{"as_of":"2026-08-10T22:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0c3682509542d9869b1bd4d97dd9ce3d3223d3d08cf432494590f1381ac7af89","coverage":[{"denominator":209,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T09:21:41.009387Z","state":"measured"},{"denominator":111,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":111,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":11,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":11,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T01:02:23.262881Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T05:27:39.626602Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":"2601.14192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-07T02:16:02.482997Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":"31754071-82a9-46af-825a-b4da22f4f634","year":2026},"citing_paper":{"arxiv_id":"2604.05719","last_updated":"2026-04-07T11:19:16Z","snapshot_observed_at":"2026-08-02T08:12:46.257370Z","submitted_at":"2026-04-07T11:19:16Z","title":"Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing","version":1},"reference_index":127,"source":"pdf_text","source_observed_at":"2026-05-10T18:52:57.225878Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2604.05719"},"observation_digest":"sha256:888de64cde324fb6c96180b5c8af288966149d5beb9d7e294dd07aa5c7acc8ad","observation_id":"91a3eaeb-71ce-4ac3-8d52-32ecaca603f9","resolution":{"observed_at":"2026-07-07T02:16:02.482997Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":"2601.14192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-07T02:16:02.482997Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":"31754071-82a9-46af-825a-b4da22f4f634","year":2026},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:e1e260b9059c8d2a70805989be254a1d2183f27971c78fd9013ffe6208458636","observation_id":"f0925a76-9055-49d1-981b-0899a721e394","resolution":{"observed_at":"2026-07-07T02:16:02.482997Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":"2601.14192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-07T02:16:02.482997Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":"31754071-82a9-46af-825a-b4da22f4f634","year":2026},"citing_paper":{"arxiv_id":"2605.09252","last_updated":"2026-05-20T19:57:19Z","snapshot_observed_at":"2026-08-02T16:03:49.427921Z","submitted_at":"2026-05-10T01:37:40Z","title":"LLM Agents Already Know When to Call Tools -- Even Without Reasoning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-05-12T02:44:00.329276Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2605.09252"},"observation_digest":"sha256:31058225103db1db4aa44df1b318eaa116c33a023286687d7c4228d05968de75","observation_id":"6f686753-c648-4ad3-81c0-570b8ecfdf27","resolution":{"observed_at":"2026-07-07T02:16:02.482997Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":"2601.14192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-07T02:16:02.482997Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":"31754071-82a9-46af-825a-b4da22f4f634","year":2026},"citing_paper":{"arxiv_id":"2605.09252","last_updated":"2026-05-20T19:57:19Z","snapshot_observed_at":"2026-08-02T16:03:49.427921Z","submitted_at":"2026-05-10T01:37:40Z","title":"LLM Agents Already Know When to Call Tools -- Even Without Reasoning","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-05-22T10:55:14.037226Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2605.09252"},"observation_digest":"sha256:3a3d1d45389292436cbe62784049e30638642a9c4ab98e2de886dfc37a84f53b","observation_id":"f7ad9586-ef4a-43b1-b154-351340a50d63","resolution":{"observed_at":"2026-07-07T02:16:02.482997Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":"2601.14192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-07T02:16:02.482997Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":"31754071-82a9-46af-825a-b4da22f4f634","year":2026},"citing_paper":{"arxiv_id":"2605.09942","last_updated":"2026-05-11T03:41:18Z","snapshot_observed_at":"2026-07-06T23:21:59.096464Z","submitted_at":"2026-05-11T03:41:18Z","title":"HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-05-12T04:14:06.843343Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2605.09942"},"observation_digest":"sha256:8390f2b375550e30c302531754bc3a7e78d370700331045bf11577bc91fd16c7","observation_id":"c379514d-2d35-47b9-9ce5-886204df19fe","resolution":{"observed_at":"2026-07-07T02:16:02.482997Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":"2601.14192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-07T02:16:02.482997Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":"31754071-82a9-46af-825a-b4da22f4f634","year":2026},"citing_paper":{"arxiv_id":"2605.19285","last_updated":"2026-05-19T03:03:32Z","snapshot_observed_at":"2026-08-08T07:33:31.662126Z","submitted_at":"2026-05-19T03:03:32Z","title":"Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-20T06:07:48.063598Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2605.19285"},"observation_digest":"sha256:81d467d8e9d0249193df906fd4c758ac4c4b3455bda70fd388f8e4047f5f811e","observation_id":"9ba0f843-d2d4-4113-9015-cd899e215546","resolution":{"observed_at":"2026-07-07T02:16:02.482997Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":"2601.14192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-07T02:16:02.482997Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":"31754071-82a9-46af-825a-b4da22f4f634","year":2026},"citing_paper":{"arxiv_id":"2606.10794","last_updated":"2026-06-10T08:17:06Z","snapshot_observed_at":"2026-08-06T14:57:05.349320Z","submitted_at":"2026-06-09T12:43:49Z","title":"READER: Robust Evidence-based Authorship Decoding via Extracted Representations","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-27T13:19:48.681128Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2606.10794"},"observation_digest":"sha256:85deb8880679b2ef4c59275486679491b1e33aa4cd86871a4b99c41c60e8707e","observation_id":"83f2f2a6-9cd4-42bf-b4e2-e45fe5981681","resolution":{"observed_at":"2026-07-07T02:16:02.482997Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-14T10:52:11.987091Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.10555","last_updated":"2026-07-12T04:04:59Z","snapshot_observed_at":"2026-08-04T22:51:41.184130Z","submitted_at":"2026-07-12T04:04:59Z","title":"Tool-Adaptive LLM Reranker","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-07-14T10:52:11.987091Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2607.10555"},"observation_digest":"sha256:b06bcd378ca9511480d54bad1f2a31dc89e0f4a81fb5919336220652449cda89","observation_id":"f20b51c9-7655-45f0-a29a-f72e6288d69b","resolution":{"observed_at":"2026-07-14T10:52:11.987091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-08-03T00:55:52.722886Z","title":"arXiv preprint arXiv:2601.14192 (2026)","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28629","last_updated":"2026-04-16T00:28:35Z","snapshot_observed_at":"2026-08-09T21:35:47.868180Z","submitted_at":"2026-04-16T00:28:35Z","title":"OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-03T00:55:52.722886Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2607.28629"},"observation_digest":"sha256:4788d40e223e4e27ea24fccbebed915b3c8d706cca272769af1d2f09bf52a6f8","observation_id":"390e5ba4-51ab-46ce-9376-0ea319be3877","resolution":{"observed_at":"2026-08-03T00:55:52.722886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-08-06T04:16:45.321886Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.01347","last_updated":"2026-08-06T05:54:32Z","snapshot_observed_at":"2026-08-09T23:10:03.366536Z","submitted_at":"2026-08-02T16:10:02Z","title":"Same Task, Different Work: Prompt-Induced Waste in Coding Agents","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T04:16:45.321886Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2608.01347"},"observation_digest":"sha256:8be27a88da3764a1067359a7f0ecc4f8475d944a94fbf1e4588ec5797d73369e","observation_id":"f1a1c7cd-b163-44a0-ba1b-963768bd9657","resolution":{"observed_at":"2026-08-06T04:16:45.321886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-08-07T01:02:23.262881Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.01347","last_updated":"2026-08-06T05:54:32Z","snapshot_observed_at":"2026-08-09T23:10:03.366536Z","submitted_at":"2026-08-02T16:10:02Z","title":"Same Task, Different Work: Prompt-Induced Waste in Coding Agents","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T01:02:23.262881Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2608.01347"},"observation_digest":"sha256:1d9eb94e33758ccf2e33615e507bf2f44ff90a9c6dc1e5eec24383d7f0516fa8","observation_id":"9dd9e399-6135-4346-b1ec-2a158b29bae9","resolution":{"observed_at":"2026-08-07T01:02:23.262881Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2601.14192/citation-record","integrity":"/paper/2601.14192/integrity","json":"/paper/2601.14192/citation-record.json","paper":"/paper/2601.14192"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:32.621359Z","title":"Lastras, Yara Rizk, and Pavan Kapanipathi","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:32.621359Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:bfa22b654738e8b51ad8f055d298704d4998d2da599887194900ea2792af2b04","observation_id":"ab2115be-b18f-4984-ae29-5e19af5a5d62","resolution":{"observed_at":"2026-08-03T09:21:32.621359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10003","last_updated":"2023-12-15T18:20:15Z","snapshot_observed_at":"2026-08-04T01:20:21.010579Z","submitted_at":"2023-12-15T18:20:15Z","title":"ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10003","snapshot_observed_at":"2026-08-03T09:21:32.684964Z","title":"Rest meets react: Self-improvement for multi-step reasoning llm agent, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:32.684964Z"},"links":{"cited_paper":"/paper/2312.10003","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:d66758dc34ca9a1d3119209442017cf29947442244f06e8285fec27e9a74b469","observation_id":"c3be1648-17fc-4441-ab3d-2bf62885c8f5","resolution":{"observed_at":"2026-08-03T09:21:32.684964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:32.758530Z","title":"Smagdi: Socratic multi agent interaction graph distillation for efficient high accuracy reasoning.arXiv preprint arXiv:2511.05528, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:32.758530Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:0cd63f66af804ded2523237b73e6862839c24d6d820b0eaa14d8de049ebda86a","observation_id":"359547e8-2526-4263-84cc-52b62b824fd7","resolution":{"observed_at":"2026-08-03T09:21:32.758530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10332","last_updated":"2023-12-16T05:43:11Z","snapshot_observed_at":"2026-08-03T13:43:49.328438Z","submitted_at":"2023-12-16T05:43:11Z","title":"ProTIP: Progressive Tool Retrieval Improves Planning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10332","snapshot_observed_at":"2026-08-03T09:21:32.891292Z","title":"Protip: Progressive tool retrieval improves planning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:32.891292Z"},"links":{"cited_paper":"/paper/2312.10332","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:4de5b49f26b86d9f0566493b64e49aa24bf92ccfbb76db397c6037f85c2604cb","observation_id":"a5e6b82f-bb8a-42c9-83f8-dc5a91588fa8","resolution":{"observed_at":"2026-08-03T09:21:32.891292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04363","last_updated":"2025-05-15T10:57:51Z","snapshot_observed_at":"2026-08-04T20:25:50.849634Z","submitted_at":"2024-07-05T09:06:47Z","title":"AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04363","snapshot_observed_at":"2026-08-03T09:21:32.969449Z","title":"Arigraph: Learning knowledge graph world models with episodic memory for llm agents.arXiv preprint arXiv:2407.04363, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:32.969449Z"},"links":{"cited_paper":"/paper/2407.04363","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:75c6a81e82ec88cd4e62430ad2bfd7f4ae25cecc279777f4d736dfcd23f040b8","observation_id":"98abe8a0-ddc0-46a5-abf9-f4240f9c30af","resolution":{"observed_at":"2026-08-03T09:21:32.969449Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:33.057646Z","title":"URLhttps://arxiv.org/abs/2506","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.057646Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:953fc03870ca6862061e1d8ce3f577b2f6f20b785b6e9e30f1c9a6f615053b2f","observation_id":"33e107ca-d598-4373-97b5-a36cd591e7c8","resolution":{"observed_at":"2026-08-03T09:21:33.057646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00663","last_updated":"2024-12-31T22:32:03Z","snapshot_observed_at":"2026-08-07T09:00:33.558814Z","submitted_at":"2024-12-31T22:32:03Z","title":"Titans: Learning to Memorize at Test Time","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00663","snapshot_observed_at":"2026-08-03T09:21:33.135922Z","title":"Titans: Learning to memorize at test time.arXiv preprint arXiv:2501.00663, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.135922Z"},"links":{"cited_paper":"/paper/2501.00663","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:9017a5ff1eff4fa4590fbf6d9111210bbf8729b6d87751c4ac18d92c4251f644","observation_id":"9377c1a8-c548-497b-a692-bcbabb7a412e","resolution":{"observed_at":"2026-08-03T09:21:33.135922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10778","last_updated":"2024-07-23T14:56:03Z","snapshot_observed_at":"2026-08-10T19:28:12.872300Z","submitted_at":"2024-02-16T16:00:50Z","title":"AutoGPT+P: Affordance-based Task Planning with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10778","snapshot_observed_at":"2026-08-03T09:21:33.227393Z","title":"Autogpt+p: Affordance-based task planning with large language models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.227393Z"},"links":{"cited_paper":"/paper/2402.10778","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:9aa8d25295c58f3eaa48e39e9755bc88f6707242be1a3f3a4e905c25198a762f","observation_id":"8eee4735-09cc-466a-ad8e-169ba509e470","resolution":{"observed_at":"2026-08-03T09:21:33.227393Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:33.262786Z","title":"Smurfs: Multi-agent system using context-efficient dfsdt for tool planning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.262786Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:1fdac75e82de6d5722c48a8df26be611be6523735d16264dc7508d522680af0b","observation_id":"b2a52966-a4da-40b5-bb64-ac0e9d956394","resolution":{"observed_at":"2026-08-03T09:21:33.262786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01620","last_updated":"2024-06-07T18:13:16Z","snapshot_observed_at":"2026-08-09T21:00:34.616174Z","submitted_at":"2024-02-02T18:35:14Z","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01620","snapshot_observed_at":"2026-08-03T09:21:33.331072Z","title":"Magdi: Structured distillation of multi-agent interaction graphs improves reasoning in smaller language models.arXiv preprint arXiv:2402.01620, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.331072Z"},"links":{"cited_paper":"/paper/2402.01620","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:9807652b155f93a753c945080c8aada2825eb4a9c1630f7e8bfe8e06b89d471c","observation_id":"28b8af0b-69c0-4484-8c04-dcbce2534b42","resolution":{"observed_at":"2026-08-03T09:21:33.331072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:33.402087Z","title":"Compress to impress: Unleashing the potential of compressive memory in real-world long-term conversations","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.402087Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:e68b4fbed27951f85f8526163d8eaa3551e7c6537b15f221912d1561908363eb","observation_id":"83e66a9e-fbb7-426e-bc0d-e41b7a357376","resolution":{"observed_at":"2026-08-03T09:21:33.402087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:33.511403Z","title":"A 2fm: An adaptive agent foundation model for tool-aware hybrid reasoning, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.511403Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:e2702002183743777757fa481a08c5db8e7b40f3fea3f5caabd4bbb4911f65b7","observation_id":"adde5d83-10df-4827-a234-ee7b697fedf2","resolution":{"observed_at":"2026-08-03T09:21:33.511403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:33.580191Z","title":"T-eval: Evaluating the tool utilization capability of large language models step by step","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.580191Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:79780b9b538b17b91f5b56828fa928983f19de9ace420945672ba2209a472795","observation_id":"06f373d2-6df7-4611-bf3c-630293b6dd06","resolution":{"observed_at":"2026-08-03T09:21:33.580191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12881","last_updated":"2024-03-19T16:26:10Z","snapshot_observed_at":"2026-08-10T09:36:07.796908Z","submitted_at":"2024-03-19T16:26:10Z","title":"Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12881","snapshot_observed_at":"2026-08-03T09:21:33.649879Z","title":"Agent-flan: Designing data and methods of effective agent tuning for large language models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.649879Z"},"links":{"cited_paper":"/paper/2403.12881","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:c2720502a07305896a2f53d0a62ce2ec96d0d92a4af6de55cbded3d318940910","observation_id":"38fa9ab9-586a-404f-96be-187b5f97a243","resolution":{"observed_at":"2026-08-03T09:21:33.649879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.19413","last_updated":"2025-04-28T01:46:35Z","snapshot_observed_at":"2026-08-02T07:32:11.339534Z","submitted_at":"2025-04-28T01:46:35Z","title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.19413","snapshot_observed_at":"2026-08-03T09:21:33.719516Z","title":"Mem0: Building production-ready ai agents with scalable long-term memory.arXiv preprint arXiv:2504.19413, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.719516Z"},"links":{"cited_paper":"/paper/2504.19413","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:c4c1ea3cbefd4cdd770beebd883e515b3029d6428f650917bf5a0e7649d179d0","observation_id":"96f8571e-eac5-49df-aac4-9c29d899c861","resolution":{"observed_at":"2026-08-03T09:21:33.719516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.11035","last_updated":"2025-09-14T01:55:01Z","snapshot_observed_at":"2026-08-04T17:14:58.509975Z","submitted_at":"2025-09-14T01:55:01Z","title":"Free-MAD: Consensus-Free Multi-Agent Debate","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.11035","snapshot_observed_at":"2026-08-03T09:21:33.800401Z","title":"Free-mad: Consensus-free multi-agent debate.arXiv preprint arXiv:2509.11035, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.800401Z"},"links":{"cited_paper":"/paper/2509.11035","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:e3563711a072ca72715dc7ec51ae575c4bf57619df05ddea19b93f8a440f7cc7","observation_id":"6e9d46b9-64d1-464d-b0a0-075173833642","resolution":{"observed_at":"2026-08-03T09:21:33.800401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11404","last_updated":"2025-05-30T16:59:23Z","snapshot_observed_at":"2026-08-07T18:13:50.766253Z","submitted_at":"2025-02-17T03:42:28Z","title":"ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11404","snapshot_observed_at":"2026-08-03T09:21:33.843234Z","title":"Toolcoder: A systematic code-empowered tool learning framework for large language models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.843234Z"},"links":{"cited_paper":"/paper/2502.11404","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:7e4ac09c4f0fc1282a30378b842a44825fe225f6105a0045e185038a3b3157dc","observation_id":"eed2dfeb-d8cb-4130-88b9-cbc78de05398","resolution":{"observed_at":"2026-08-03T09:21:33.843234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:33.923266Z","title":"AnyTool: Self-reflective, hierarchical agents for large-scale API calls","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:33.923266Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:e918220bfc26be0194329a8e256b3fdf7484fa6a5aba79af9189d11d9341c818","observation_id":"3a5f7ed1-5318-4307-b0f3-11051529602d","resolution":{"observed_at":"2026-08-03T09:21:33.923266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:34.004778Z","title":"Tinyagent: Function calling at the edge","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.004778Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:98396663ec98ef4108be2899b15b41ee14a0ed400259570cc887ac90af4eec8f","observation_id":"99c60687-ad5e-47dd-9045-d89bd603a2dc","resolution":{"observed_at":"2026-08-03T09:21:34.004778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:34.079017Z","title":"Cost-of-pass: An economic framework for evaluating language models.arXiv preprint arXiv:2504.13359, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.079017Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:7f2783e0373e87004511b25cb57ba24f0f68b5191505adbcbda349a6436ba496","observation_id":"d0c5cdee-2697-48b6-a32a-f41a469369fe","resolution":{"observed_at":"2026-08-03T09:21:34.079017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.18866","last_updated":"2026-02-28T11:55:50Z","snapshot_observed_at":"2026-07-06T22:33:43.999976Z","submitted_at":"2025-10-21T17:58:17Z","title":"LightMem: Lightweight and Efficient Memory-Augmented Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.18866","snapshot_observed_at":"2026-08-03T09:21:34.187283Z","title":"Lightmem: Lightweight and efficient memory-augmented generation.arXiv preprint arXiv:2510.18866, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.187283Z"},"links":{"cited_paper":"/paper/2510.18866","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:d89c87d02ea8a6167e720c7337dcf0fb77dbba70ba9132b0076c7b8a88530f38","observation_id":"896e0749-3f05-4d1a-844a-ffb38a17f9a2","resolution":{"observed_at":"2026-08-03T09:21:34.187283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.11536","last_updated":"2025-04-17T16:46:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-15T18:10:22Z","title":"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.11536","snapshot_observed_at":"2026-08-03T09:21:34.256595Z","title":"Retool: Reinforcement learning for strategic tool use in llms, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.256595Z"},"links":{"cited_paper":"/paper/2504.11536","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:3fcb19bc1df35ab4286a30ca057724e23bbfba3733fa19a174e0f40278ad4167","observation_id":"8f431bec-d49d-4f73-a077-e2387f5fd81f","resolution":{"observed_at":"2026-08-03T09:21:34.256595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.07464","last_updated":"2025-01-08T07:25:55Z","snapshot_observed_at":"2026-08-08T03:53:06.264924Z","submitted_at":"2024-11-12T00:57:30Z","title":"BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.07464","snapshot_observed_at":"2026-08-03T09:21:34.359341Z","title":"Budgetmlagent: A cost- effective llm multi-agent system for automating machine learning tasks, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.359341Z"},"links":{"cited_paper":"/paper/2411.07464","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:b8317e36788cbf15518c95d950474fddbbd5dec46455928535cf8d31fc7b7d1f","observation_id":"752ac824-c44a-4220-9426-169036fc5778","resolution":{"observed_at":"2026-08-03T09:21:34.359341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:34.451943Z","title":"Memory sharing for large language model based agents.arXiv preprint arXiv:2404.09982, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.451943Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:610ae0a2d981945017c2a57cff153a42f44013f3e1ba3c9292cfaa3708401436","observation_id":"51a6cb35-b79b-4cc7-9e15-6a766db0391b","resolution":{"observed_at":"2026-08-03T09:21:34.451943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17464","last_updated":"2025-01-08T16:27:29Z","snapshot_observed_at":"2026-08-10T11:45:14.219740Z","submitted_at":"2024-01-30T21:53:30Z","title":"Efficient Tool Use with Chain-of-Abstraction Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.17464","snapshot_observed_at":"2026-08-03T09:21:34.524100Z","title":"Efficient tool use with chain-of- abstraction reasoning, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.524100Z"},"links":{"cited_paper":"/paper/2401.17464","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:659c770b2fc07fe08d7b399967785a5b00a698848500448518ba01168df3e2cc","observation_id":"d61ff02f-6270-422f-a14e-926f9105e8a8","resolution":{"observed_at":"2026-08-03T09:21:34.524100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:34.618766Z","title":"Mcp-radar: A multi-dimensional benchmark for evaluating tool use capabilities in large language models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.618766Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:7fa20654a79edf48fcd3863e35cd019bb7510226fb573aff68f7f6b3fbaf9879","observation_id":"cdd9e361-897d-46cd-8c44-675ac3c55bc4","resolution":{"observed_at":"2026-08-03T09:21:34.618766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:34.728902Z","title":"Learning to forget: Continual prediction with lstm.Neural computation, 12(10):2451–2471, 2000","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.728902Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:d57370c3b62121ca601b5e3dabc07c4c670e40a52ada5a11455ac4375c25c9dd","observation_id":"83472e04-bd97-405d-8430-7e783eb03e11","resolution":{"observed_at":"2026-08-03T09:21:34.728902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:34.777838Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.777838Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:c096cdeb61143e953126b0d766338ca45d49ba81b45d325cf58e6e87e907fae2","observation_id":"1bd60d80-31f8-4392-b65a-39868b56d6c7","resolution":{"observed_at":"2026-08-03T09:21:34.777838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18864","last_updated":"2025-02-26T06:17:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-26T06:17:13Z","title":"Towards an AI co-scientist","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18864","snapshot_observed_at":"2026-08-03T09:21:34.908718Z","title":"Towards an ai co- scientist: A multi-agent system for scientific discovery.arXiv preprint arXiv:2502.18864, page 3, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.908718Z"},"links":{"cited_paper":"/paper/2502.18864","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:78a1b1a5acfdb07b4af4ab0ab7db251ea75f2bea63b2515b5a721dd4a2a163f5","observation_id":"fb3e7c4b-8086-47a4-8245-c4ef6cc06164","resolution":{"observed_at":"2026-08-03T09:21:34.908718Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07714","last_updated":"2025-03-05T07:39:03Z","snapshot_observed_at":"2026-08-05T00:50:54.678872Z","submitted_at":"2024-03-12T14:57:40Z","title":"StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07714","snapshot_observed_at":"2026-08-03T09:21:34.979167Z","title":"Stabletoolbench: Towards stable large-scale benchmarking on tool learning of large language models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:34.979167Z"},"links":{"cited_paper":"/paper/2403.07714","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:8d3d02c9517e04417846b42391eaf5921b73ccc843b71d990fedfe43fbc55954","observation_id":"20ee8583-fa32-4e82-8269-ef8aeed25810","resolution":{"observed_at":"2026-08-03T09:21:34.979167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:35.115026Z","title":"Legomem: Modular procedural memory for multi-agent llm systems for workflow automation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:35.115026Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:3bdc1cc42cf8a41b295e7fb9a546799648b58622a587fd77fc3631a3cae620dc","observation_id":"1e063aae-f4f5-449f-9673-8b03624a0f9e","resolution":{"observed_at":"2026-08-03T09:21:35.115026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.11805","last_updated":"2025-01-07T13:34:06Z","snapshot_observed_at":"2026-07-06T19:34:01.458836Z","submitted_at":"2024-10-15T17:33:43Z","title":"NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.11805","snapshot_observed_at":"2026-08-03T09:21:35.231304Z","title":"Nestools: A dataset for evaluating nested tool learning abilities of large language models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:35.231304Z"},"links":{"cited_paper":"/paper/2410.11805","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:fc64c0f0b288821941825ebf22f230761d22e99b6671155e9dcee2ba90570007","observation_id":"7d38cb52-5598-483f-84fe-03b8ec11ab1d","resolution":{"observed_at":"2026-08-03T09:21:35.231304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:35.349702Z","title":"Toolkengpt: Augmenting frozen language models with massive tools via tool embeddings","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:35.349702Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:0f603e28bba1c459f48e182c9441eb374c1a8b00470c6e6cf9596fd8ce81572b","observation_id":"54d84ce5-51a2-4b18-a040-19a105b7242a","resolution":{"observed_at":"2026-08-03T09:21:35.349702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:35.464008Z","title":"WebVoyager: Building an end-to-end web agent with large multimodal models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:35.464008Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:b58bfc2c7292da25f313a7bc64c349cd16dc0a62e178a72b3292106c7012ff1b","observation_id":"4300c3e1-2cdf-440c-a19c-e6b095d44f03","resolution":{"observed_at":"2026-08-03T09:21:35.464008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:35.715232Z","title":"Diffthinker: Towards generative multimodal reasoning with diffusion models.arXiv preprint arXiv:2512.24165, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:35.715232Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:e0a35c705aaf81706012bc23c24aa670cdaecfe5d6d31839615fc850b3c75755","observation_id":"4121356e-366c-4c97-a37b-4a28c41705ca","resolution":{"observed_at":"2026-08-03T09:21:35.715232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:35.777067Z","title":"Planning without search: Refining frontier llms with offline goal-conditioned rl, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:35.777067Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:ecb75166918549df5fab06ffbae504b5b08f1fafdccdb0afb00e708726cd88ef","observation_id":"a83ea6ae-1567-47f1-b4f5-27b426547087","resolution":{"observed_at":"2026-08-03T09:21:35.777067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:35.859334Z","title":"Metagpt: Meta programming for a multi- agent collaborative framework","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:35.859334Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:5fee80290bbee3b9068fbe889679a843be69aa1b4248f18a66304d985e749999","observation_id":"bc0dae43-11e9-418e-9213-804c27dc1400","resolution":{"observed_at":"2026-08-03T09:21:35.859334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:35.969830Z","title":"Cogagent: Avisual language modelforgui agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:35.969830Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:195e50f5a77b32646cbc3c466f5279f68dfc86fd8d1d8de10c631911fa940bcc","observation_id":"20cf7606-8709-4189-a7e2-ebf0e969e202","resolution":{"observed_at":"2026-08-03T09:21:35.969830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:36.042220Z","title":"my agent understands me better","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.042220Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:7091cc1e74e04434c0acaeb413c0447e15e3b5d14b37e84221b1ae3ba6f7a8a0","observation_id":"c3dd3400-2d92-42d1-9147-93067591c89b","resolution":{"observed_at":"2026-08-03T09:21:36.042220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:36.114716Z","title":"Hiagent: Hierar- chical working memory management for solving long-horizon agent tasks with large language model","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.114716Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:4c36922ccd6d67af4a1df3d1966adac2f9899917b1fe29ebf23d424f3d693d02","observation_id":"fb2393e6-3d25-476c-b7e1-dfcdeca7ff60","resolution":{"observed_at":"2026-08-03T09:21:36.114716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17167","last_updated":"2024-06-03T11:28:29Z","snapshot_observed_at":"2026-07-06T17:22:37.193255Z","submitted_at":"2024-01-30T16:52:56Z","title":"Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.17167","snapshot_observed_at":"2026-08-03T09:21:36.199978Z","title":"Planning, creation, usage: Benchmarking llms for comprehensive tool utilization in real-world complex scenarios, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.199978Z"},"links":{"cited_paper":"/paper/2401.17167","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:f3d5c50cb62d1596ccb10cebbe5034dc6bac7cbd30ecd37ff4f3fa1d28fa259d","observation_id":"ce6a98af-01ee-4af3-a5b5-50a5ca6356c1","resolution":{"observed_at":"2026-08-03T09:21:36.199978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03128","last_updated":"2024-12-04T19:49:02Z","snapshot_observed_at":"2026-07-06T16:27:55.509482Z","submitted_at":"2023-10-04T19:39:26Z","title":"MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03128","snapshot_observed_at":"2026-08-03T09:21:36.280577Z","title":"Metatool benchmark for large language models: Deciding whether to use tools and which to use, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.280577Z"},"links":{"cited_paper":"/paper/2310.03128","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:f65645b9bb9555c784e1f1064c91539878b539734ae4e96d909d22cfcf8e71b4","observation_id":"ad97d443-4774-437f-b967-c37f48d6ce05","resolution":{"observed_at":"2026-08-03T09:21:36.280577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07596","last_updated":"2025-05-12T14:21:57Z","snapshot_observed_at":"2026-08-07T15:47:51.293460Z","submitted_at":"2025-05-12T14:21:57Z","title":"Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07596","snapshot_observed_at":"2026-08-03T09:21:36.356795Z","title":"Reinforced internal-external knowledge synergistic reasoning for efficient adaptive search agent.arXiv preprint arXiv:2505.07596, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.356795Z"},"links":{"cited_paper":"/paper/2505.07596","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:dcf121a37936f20a819459f240ec441b5372a2842e5e6d525b61c7ed430c5e38","observation_id":"6079eaaa-96a9-41c0-bb31-bd7465ac2de2","resolution":{"observed_at":"2026-08-03T09:21:36.356795Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21276","last_updated":"2024-10-25T17:43:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-25T17:43:01Z","title":"GPT-4o System Card","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21276","snapshot_observed_at":"2026-08-03T09:21:36.440222Z","title":"Gpt-4o system card.arXiv preprint arXiv:2410.21276, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.440222Z"},"links":{"cited_paper":"/paper/2410.21276","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:2f8368fd03836ec3b412764bc9dc7e7dcb32740893b927c529c6b6fe0e3630ba","observation_id":"e1d9baf2-6c39-4f9f-bedb-668c32fce50f","resolution":{"observed_at":"2026-08-03T09:21:36.440222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.06278","last_updated":"2026-07-26T14:15:22Z","snapshot_observed_at":"2026-08-09T07:39:46.027693Z","submitted_at":"2025-09-08T02:00:31Z","title":"TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.06278","snapshot_observed_at":"2026-08-03T09:21:36.494112Z","title":"Tablemind: An autonomousprogrammaticagentfortool-augmentedtablereasoning.arXivpreprintarXiv:2509.06278, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.494112Z"},"links":{"cited_paper":"/paper/2509.06278","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:688ebd0e0b72694cfff6e0391daf3ff6b314a9d8975c35e3b9bbbd882ac8bbe8","observation_id":"3c8c4177-a9f3-4cb5-8a7f-7503affc50ad","resolution":{"observed_at":"2026-08-03T09:21:36.494112Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:36.553147Z","title":"KG-agent: An efficient autonomous agent framework for complex reasoning over knowledge graph","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.553147Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:0805ac53352d27986b8ee49d28811338bea0b49162e3f0f6f9d53ae017333d75","observation_id":"a6e5dd17-27f6-42f7-a094-bd91f37b44a1","resolution":{"observed_at":"2026-08-03T09:21:36.553147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:36.628850Z","title":"SWE-bench: Can language models resolve real-world github issues? InThe Twelfth International Conference on Learning Representations, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.628850Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:05359c4dda4ad105066534aca8b09420d33702d6cffa20b6c2c41935e8ab84df","observation_id":"a0f3d9d3-553d-43ba-aa33-8b4c9192386a","resolution":{"observed_at":"2026-08-03T09:21:36.628850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:36.743923Z","title":"Benchmark for planning and control with large language model agents: Blocksworld with model context protocol.arXiv preprint arXiv:2512.03955, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.743923Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:0d62e27d83149264746362b4c1d73cee80262b64b01d1b193e37f838c8267a34","observation_id":"4248f289-9767-471b-b158-a02f0cb39e2b","resolution":{"observed_at":"2026-08-03T09:21:36.743923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:36.821627Z","title":"Memory OS of AI agent","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.821627Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:2f6b4a8f9928f45ec1e04c0c7e1309c3a4926625f1d80e0e46a41c46c7440f2b","observation_id":"f6be6846-c53a-4160-a25c-b4443e26e093","resolution":{"observed_at":"2026-08-03T09:21:36.821627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:36.885088Z","title":"Distilling llm agent into small models with retrieval and code tools, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.885088Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:b763c526c6985378d2b5b58657209ca7eb4eac80ec9305982da342ecb2bbd7e5","observation_id":"7b233e19-56da-4a18-8183-059c31161fa3","resolution":{"observed_at":"2026-08-03T09:21:36.885088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:36.971942Z","title":"An llm compiler for parallel function calling","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:36.971942Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:c8f3bd631ed282250db2064bdc5e5fa644b12cef3ac550e8accebd145df25baf","observation_id":"94aca765-928a-4ebc-b252-ab1f7bcd085a","resolution":{"observed_at":"2026-08-03T09:21:36.971942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.030210Z","title":"Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.030210Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:dea8a19c6609aed74c2233aaffd4c3a44292b900348573d312ceec148587c7da","observation_id":"14a6671d-96c9-485c-a4b5-bcc65a9b5505","resolution":{"observed_at":"2026-08-03T09:21:37.030210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.082374Z","title":"Convolutional networks for images, speech, and time series.The handbook of brain theory and neural networks, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.082374Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:f11b31411e5e8e01b29edc8e78cca7091c1c375d8cd48ef239fab222635234d9","observation_id":"d7c5b6b5-4754-482f-8afb-5f372f1e59df","resolution":{"observed_at":"2026-08-03T09:21:37.082374Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.144490Z","title":"A human-inspired reading agent with gist memory of very long contexts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.144490Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:d81986075fc9dd1bbae9867f957ccada81b230e198f08e17abac4376fc7dc5ad","observation_id":"8e689c0b-3802-4e90-aa3d-a1bacd0bc1e2","resolution":{"observed_at":"2026-08-03T09:21:37.144490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.196681Z","title":"D-smart: Enhancingllmdialogueconsistencyviadynamicstructured memory and reasoning tree.arXiv preprint arXiv:2510.13363, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.196681Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:5cb3bcd94ccd3fb820e6f704e6b9ffcfcecc92216f334c1b423bd7c8368cc22b","observation_id":"322efaba-95a6-464e-8aa4-d04272ba443c","resolution":{"observed_at":"2026-08-03T09:21:37.196681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.268309Z","title":"Camel: Commu- nicative agents for\" mind\" exploration of large language model society.Advances in Neural Information Processing Systems, 36:51991–52008, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.268309Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:35e0f818774fe036c78cbfc5b0a7922d580d9d9cb61ddd649a3a3e2b4f0e613b","observation_id":"f4b18201-4260-4afb-974d-c596c5d93c1d","resolution":{"observed_at":"2026-08-03T09:21:37.268309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.331318Z","title":"Hello again! llm-powered personalized agent for long-term dialogue","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.331318Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:717282d084b034abbaf150d9fd6d7be55c3d65c9eace044ba9d5f34c8b43a821","observation_id":"5dcd4162-f908-4c01-8cd6-bef4f87248b3","resolution":{"observed_at":"2026-08-03T09:21:37.331318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.415481Z","title":"Seek in the dark: Reasoning via test-time instance-level policy gradient in latent space, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.415481Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:c4d8de3128aec2f664b7a1068803d6612a8cec92feddb7859a829a79db8bdd37","observation_id":"2d922c67-e76f-4dd9-8099-4a40793db628","resolution":{"observed_at":"2026-08-03T09:21:37.415481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.494275Z","title":"API-bank: A comprehensive benchmark for tool-augmented LLMs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.494275Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:f3d3ee97d76e7fc72ef8067f077de1533f52560debce15aa16b5e115fcf83f90","observation_id":"2aadaafc-7fc4-4b48-b1f7-c8a1cb07346b","resolution":{"observed_at":"2026-08-03T09:21:37.494275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.586887Z","title":"GraphReader: Building graph-based agent to enhance long-context abilities of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.586887Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:a962454e923e755f98b6ac77abbd92b30ddc5bd4694ac316136bd726dcf636e2","observation_id":"15d902ba-bdde-474b-aefd-31669c493d90","resolution":{"observed_at":"2026-08-03T09:21:37.586887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:37.674892Z","title":"Optimus-1: Hybrid multimodal memory empowered agents excel in long-horizon tasks.Advances in neural information processing systems, 37:49881–49913, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.674892Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:305a0f5b9ee1d20a674e2d7b1112116a1a795e62c5a756f98c4581336fe2a0a3","observation_id":"c7edb603-bdec-4aa8-a829-55efa5cd3956","resolution":{"observed_at":"2026-08-03T09:21:37.674892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.19598","last_updated":"2025-08-27T06:19:50Z","snapshot_observed_at":"2026-08-05T15:44:13.449330Z","submitted_at":"2025-08-27T06:19:50Z","title":"Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.19598","snapshot_observed_at":"2026-08-03T09:21:37.725866Z","title":"Encouraging good processes without the need for good answers: Reinforcement learning for llm agent planning, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.725866Z"},"links":{"cited_paper":"/paper/2508.19598","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:c17da98a6316cafe6bfc07cf0acdfd7a9a259619a461910863c0c4ef940f647f","observation_id":"9bbb342f-ef02-4469-84c5-6a21c09fd136","resolution":{"observed_at":"2026-08-03T09:21:37.725866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.03724","last_updated":"2025-12-03T03:19:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-04T17:21:46Z","title":"MemOS: A Memory OS for AI System","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.03724","snapshot_observed_at":"2026-08-03T09:21:37.792152Z","title":"Memos: A memory os for ai system.arXiv preprint arXiv:2507.03724, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.792152Z"},"links":{"cited_paper":"/paper/2507.03724","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:13cc77e1d311b4271a4d98af0e516ec6c422da9ca40ae2e2e3eebb3d56c95df2","observation_id":"e16c50f8-406e-4207-8dfe-e93c1d9019de","resolution":{"observed_at":"2026-08-03T09:21:37.792152Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.17390","last_updated":"2023-12-06T10:07:01Z","snapshot_observed_at":"2026-07-06T15:34:16.800916Z","submitted_at":"2023-05-27T07:04:15Z","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.17390","snapshot_observed_at":"2026-08-03T09:21:37.853241Z","title":"Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.853241Z"},"links":{"cited_paper":"/paper/2305.17390","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:c4e9d2b443c57998722ba9418fb46684aee61fb93ac5f5f62cfd1c5c65d6d03a","observation_id":"45ae83e9-3a82-4e05-909b-d4179d9b329f","resolution":{"observed_at":"2026-08-03T09:21:37.853241Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02805","last_updated":"2024-06-03T13:07:06Z","snapshot_observed_at":"2026-08-09T10:06:19.273396Z","submitted_at":"2024-02-05T08:26:33Z","title":"Graph-enhanced Large Language Models in Asynchronous Plan Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.02805","snapshot_observed_at":"2026-08-03T09:21:37.905119Z","title":"Pierrehumbert","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:37.905119Z"},"links":{"cited_paper":"/paper/2402.02805","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:41546acc5623236fa94595a126ff1ea4870638c9d6a5de72d5e6d8662fc22115","observation_id":"f85dd198-16f7-40c8-a237-320cb95ef6e3","resolution":{"observed_at":"2026-08-03T09:21:37.905119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:38.052409Z","title":"Stop wasting your tokens: Towards efficient runtime multi-agent systems.arXiv preprint arXiv:2510.26585, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.052409Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:8c09a8cb6a9e2dbffb8cb526002ae02a57295f177c8f6086f402cd360d5f2599","observation_id":"20f69a48-36f4-42b2-9b33-b00ddd522445","resolution":{"observed_at":"2026-08-03T09:21:38.052409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.02584","last_updated":"2025-02-04T18:58:31Z","snapshot_observed_at":"2026-08-09T11:38:31.414567Z","submitted_at":"2025-02-04T18:58:31Z","title":"QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.02584","snapshot_observed_at":"2026-08-03T09:21:38.122828Z","title":"Qlass: Boosting language agent inference via q-guided stepwise search.arXiv preprint arXiv:2502.02584, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.122828Z"},"links":{"cited_paper":"/paper/2502.02584","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:f0e1f7ca00cee804f306c00c252d9a83085786a54af4a1e3987df8324cebded3","observation_id":"e7bfb37c-3499-4b1f-8335-979f89b7ab03","resolution":{"observed_at":"2026-08-03T09:21:38.122828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.02734","last_updated":"2026-06-29T03:11:56Z","snapshot_observed_at":"2026-08-04T00:12:30.501128Z","submitted_at":"2025-11-04T16:58:29Z","title":"CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.02734","snapshot_observed_at":"2026-08-03T09:21:38.206487Z","title":"Costbench: Evaluating multi-turn cost-optimal planning and adaptation in dynamic environments for llm tool-use agents.arXiv preprint arXiv:2511.02734, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.206487Z"},"links":{"cited_paper":"/paper/2511.02734","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:7cafe106db577ff87ed8a83b064261692afc2289b5d989b7b0d2b90b5f5b75b3","observation_id":"72ae211f-f97f-4dec-88e8-fde96dc5d8ff","resolution":{"observed_at":"2026-08-03T09:21:38.206487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.04903","last_updated":"2025-08-12T16:29:05Z","snapshot_observed_at":"2026-08-05T23:47:37.018948Z","submitted_at":"2025-08-06T21:59:34Z","title":"RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.04903","snapshot_observed_at":"2026-08-03T09:21:38.288048Z","title":"Rcr-router: Efficient role-aware context routing for multi-agent llm systems with structured memory.arXiv preprint arXiv:2508.04903, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.288048Z"},"links":{"cited_paper":"/paper/2508.04903","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:75d8fa290e51434c2f82854022276001e5846836f1dec5133ff570c4ba52d6f8","observation_id":"ada2545f-ead5-4804-8c81-bb2dbdd521c1","resolution":{"observed_at":"2026-08-03T09:21:38.288048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:38.372463Z","title":"Toolscope: Enhancing llm agent tool use through tool merging and context-aware filtering,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.372463Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:9047b2ce5b445d62a4c99b4d4d1a69593946149809a369f993d75be5bffa1f8b","observation_id":"bc9319f8-2e6a-49ae-87d4-397d8729303d","resolution":{"observed_at":"2026-08-03T09:21:38.372463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:38.518720Z","title":"Lost in the middle: How language models use long contexts.Transactions of the Association for Computational Linguistics, 12:157–173, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.518720Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:e40d9bd0c7bbfd6875fff3428b69c2bd618bfaad80d8e42d664abd43ce46b4ca","observation_id":"4f2e88de-1c33-4bcb-b58c-f75f69e75879","resolution":{"observed_at":"2026-08-03T09:21:38.518720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:38.600837Z","title":"Budget-aware tool-use enables effective agent scaling, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.600837Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:ac8b60d427dc82e2b398bf8df0d55fb8e1d01cd4fb11e4500a37e7bf20406b51","observation_id":"c5e5e3ec-0b41-4464-a183-d20676753b23","resolution":{"observed_at":"2026-08-03T09:21:38.600837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:38.684047Z","title":"Groupdebate: Enhancing the efficiency of multi-agent debate using group discussion.arXiv preprint arXiv:2409.14051, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.684047Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:67241ff3c45e29e6c14915d066472caf44c117c5aad5bfa3c291f1e2c69e9d7b","observation_id":"d3e3ec54-736e-49d7-abfc-e7bdcdb17ef3","resolution":{"observed_at":"2026-08-03T09:21:38.684047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04575","last_updated":"2025-01-08T15:45:21Z","snapshot_observed_at":"2026-08-10T21:27:03.875743Z","submitted_at":"2025-01-08T15:45:21Z","title":"InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.04575","snapshot_observed_at":"2026-08-03T09:21:38.736786Z","title":"Infiguiagent: A multimodal generalist gui agent with native reasoning and reflection, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.736786Z"},"links":{"cited_paper":"/paper/2501.04575","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:98b4c05061312a283967f12b1ff0024366c881b35ad7542b2ae4c4f3a1af4c2f","observation_id":"da9d842c-fb0b-409a-9eac-67a320d0e116","resolution":{"observed_at":"2026-08-03T09:21:38.736786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.06292","last_updated":"2024-09-01T00:41:18Z","snapshot_observed_at":"2026-07-06T18:59:43.564435Z","submitted_at":"2024-08-12T16:58:11Z","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.06292","snapshot_observed_at":"2026-08-03T09:21:38.808252Z","title":"The ai scientist: Towards fully automated open-ended scientific discovery.arXiv preprint arXiv:2408.06292, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.808252Z"},"links":{"cited_paper":"/paper/2408.06292","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:ce290fc0609648994603f65b98e510da2e3223eeb4ec115994322b006f09cede","observation_id":"651d74e8-9cbf-463a-83cf-ce5807ce259f","resolution":{"observed_at":"2026-08-03T09:21:38.808252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08239","last_updated":"2023-08-23T03:37:04Z","snapshot_observed_at":"2026-08-10T06:25:18.141838Z","submitted_at":"2023-08-16T09:15:18Z","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08239","snapshot_observed_at":"2026-08-03T09:21:38.865918Z","title":"Memochat: Tuning llms to use memos for consistent long-range open-domain conversation.arXiv preprint arXiv:2308.08239, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.865918Z"},"links":{"cited_paper":"/paper/2308.08239","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:9eda70d7f304d0a042a4653974b2a1c141fc6ea5524a3bed9c87963b96318e38","observation_id":"bdfe5e82-71e2-4c0c-af81-ce2bcce1cc25","resolution":{"observed_at":"2026-08-03T09:21:38.865918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14594","last_updated":"2024-10-22T16:27:12Z","snapshot_observed_at":"2026-07-06T19:36:05.879892Z","submitted_at":"2024-10-18T16:44:22Z","title":"Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Bases","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.14594","snapshot_observed_at":"2026-08-03T09:21:38.925211Z","title":"Toolshed: Scale tool-equipped agents with advanced rag-tool fusion and tool knowledge bases","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.925211Z"},"links":{"cited_paper":"/paper/2410.14594","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:79d77b815a631438b76d935c36948c847f99c0026eb45c9a562165d9217d8f69","observation_id":"4103d44a-bc6b-4c06-8de7-e5422b1f164f","resolution":{"observed_at":"2026-08-03T09:21:38.925211Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11451","last_updated":"2024-02-21T03:04:49Z","snapshot_observed_at":"2026-08-10T02:30:38.188398Z","submitted_at":"2024-02-18T04:19:44Z","title":"SciAgent: Tool-augmented Language Models for Scientific Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11451","snapshot_observed_at":"2026-08-03T09:21:38.987928Z","title":"Sciagent: Tool-augmented language models for scientific reasoning.arXiv preprint arXiv:2402.11451, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:38.987928Z"},"links":{"cited_paper":"/paper/2402.11451","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:9e362c7504df4e30e492f020bf2f2f1c0aff1872852ba25b2ab9b3f905982be7","observation_id":"683abec8-e12b-47d0-9ce3-5afd08ac6b6e","resolution":{"observed_at":"2026-08-03T09:21:38.987928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:39.050709Z","title":"Evaluating very long-term conversational memory of LLM agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.050709Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:652d303b80114d0bbd88c6d7aef952cd1ba91061b159dfe293a2ca57bb0142e5","observation_id":"3601df2b-0c42-4713-b380-b46edd0c0ace","resolution":{"observed_at":"2026-08-03T09:21:39.050709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:39.109824Z","title":"Gaia: a benchmarkforgeneralaiassistants","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.109824Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:7f87795eb8f48fe8d749ca719a0bc267302b6a1bea78ab5be2ce6541fede83a5","observation_id":"4477cfcf-b7d2-43b3-8e33-963646ff9f50","resolution":{"observed_at":"2026-08-03T09:21:39.109824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.02141","last_updated":"2024-09-02T19:39:24Z","snapshot_observed_at":"2026-08-09T20:10:50.076038Z","submitted_at":"2024-09-02T19:39:24Z","title":"Efficient and Scalable Estimation of Tool Representations in Vector Space","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.02141","snapshot_observed_at":"2026-08-03T09:21:39.171841Z","title":"Efficient and scalable estimation of tool representations in vector space.arXiv preprint arXiv:2409.02141, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.171841Z"},"links":{"cited_paper":"/paper/2409.02141","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:afe04e152447cfca8d7ca7e191771011bb0aaed02df776cb41a8b6889d65c593","observation_id":"f40ece36-cef3-461e-9661-aa33357af025","resolution":{"observed_at":"2026-08-03T09:21:39.171841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.13131","last_updated":"2025-06-16T06:37:18Z","snapshot_observed_at":"2026-08-07T04:21:43.190472Z","submitted_at":"2025-06-16T06:37:18Z","title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.13131","snapshot_observed_at":"2026-08-03T09:21:39.263268Z","title":"Alphaevolve: A coding agent for scientific and algorithmic discovery.arXiv preprint arXiv:2506.13131, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.263268Z"},"links":{"cited_paper":"/paper/2506.13131","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:a01926eb6ba3dbaa4c833f15f3713bdf8a298d70129302520f43a760947de7c8","observation_id":"fbaaf212-6841-4168-99cc-7d87f4b8b67c","resolution":{"observed_at":"2026-08-03T09:21:39.263268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.25140","last_updated":"2026-03-16T20:49:28Z","snapshot_observed_at":"2026-08-02T12:08:17.149184Z","submitted_at":"2025-09-29T17:51:03Z","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.25140","snapshot_observed_at":"2026-08-03T09:21:39.365445Z","title":"Reasoningbank: Scaling agent self-evolving with reasoning memory","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.365445Z"},"links":{"cited_paper":"/paper/2509.25140","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:7049c4f755a495b211ac0affd1091214c358045d071be4aabc60cbd8d549cf0e","observation_id":"309f7089-5a3b-46ff-b251-015d0dd85304","resolution":{"observed_at":"2026-08-03T09:21:39.365445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08560","last_updated":"2024-02-12T18:59:46Z","snapshot_observed_at":"2026-08-09T03:13:16.831626Z","submitted_at":"2023-10-12T17:51:32Z","title":"MemGPT: Towards LLMs as Operating Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08560","snapshot_observed_at":"2026-08-03T09:21:39.474568Z","title":"Memgpt: Towards llms as operating systems.arXiv preprint arXiv:2310.08560, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.474568Z"},"links":{"cited_paper":"/paper/2310.08560","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:adffd9eb7dcb54ba06fc2570b1afd69e07c93a42cef574dbdae49da209117516","observation_id":"98ce77ad-a6d1-4272-b249-e90587be6069","resolution":{"observed_at":"2026-08-03T09:21:39.474568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:39.568482Z","title":"Learning when to plan: Efficiently allocating test-time compute for llm agents, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.568482Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:ca09234ac3a985df13ef8c71cfdef3f3183b796ae5c9670d60283a678864fd14","observation_id":"4d073623-71f4-448c-9480-dfc29628b40f","resolution":{"observed_at":"2026-08-03T09:21:39.568482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:39.665291Z","title":"Secom: On memory construction and retrieval for personalized conversational agents","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.665291Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:df74bef18284f4b82ecb2150763287de4cde625c7192255598faa6e90793879b","observation_id":"ccbc07ce-699e-4ccc-a981-5b1599b00bf2","resolution":{"observed_at":"2026-08-03T09:21:39.665291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:39.796164Z","title":"Generative agents: Interactive simulacra of human behavior","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.796164Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:eeaa0d1b74bfd93bf3c2b67ab786b5abebb8d71b1cc2368dd45f680d2524f077","observation_id":"b95ad98c-cb82-4b9a-b837-8b9e182239ab","resolution":{"observed_at":"2026-08-03T09:21:39.796164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:39.983428Z","title":"Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:39.983428Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:3d1b75e833c97774fc0046975b015bb81bfed967e65ace72cceb9e160c6ec3a0","observation_id":"c48f5862-bf56-4fb5-a5ba-dc36d6477589","resolution":{"observed_at":"2026-08-03T09:21:39.983428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.01062","last_updated":"2026-04-09T17:44:11Z","snapshot_observed_at":"2026-07-06T21:34:38.683177Z","submitted_at":"2025-06-01T16:04:34Z","title":"SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.01062","snapshot_observed_at":"2026-08-03T09:21:40.124717Z","title":"Sealqa: Raising the bar for reasoning in search-augmented language models.arXiv preprint arXiv:2506.01062, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.124717Z"},"links":{"cited_paper":"/paper/2506.01062","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:d0caf1c8a10146825d6c213fad3d2b2db58dd0f196757bb537035872b62ae1d0","observation_id":"144e0341-44c8-416f-b268-364d6005d727","resolution":{"observed_at":"2026-08-03T09:21:40.124717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:40.246506Z","title":"Consensagent: Towards efficient and effective consensus in multi-agent llm interactions through sycophancy mitigation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.246506Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:a681d5ed02f11cce53eaab1954a6676f4e995e6c69b5f113948468c1b1beb553","observation_id":"c7a3cfe4-0fcd-4503-81d5-58131dc24e86","resolution":{"observed_at":"2026-08-03T09:21:40.246506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07155","last_updated":"2025-03-17T00:22:42Z","snapshot_observed_at":"2026-08-07T19:31:15.812384Z","submitted_at":"2024-06-11T11:02:04Z","title":"Scaling Large Language Model-based Multi-Agent Collaboration","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07155","snapshot_observed_at":"2026-08-03T09:21:40.335251Z","title":"Scaling large language model-based multi-agent collaboration.arXiv preprint arXiv:2406.07155, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.335251Z"},"links":{"cited_paper":"/paper/2406.07155","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:abcaf1c23e5d565c1843c1c04e6c3690d9d826d2619627ef134e76ae1dff246d","observation_id":"19c19a19-f081-4ce8-b363-75da2db9b538","resolution":{"observed_at":"2026-08-03T09:21:40.335251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13958","last_updated":"2025-04-16T21:45:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-16T21:45:32Z","title":"ToolRL: Reward is All Tool Learning Needs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13958","snapshot_observed_at":"2026-08-03T09:21:40.391396Z","title":"Toolrl: Reward is all tool learning needs.arXiv preprint arXiv:2504.13958, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.391396Z"},"links":{"cited_paper":"/paper/2504.13958","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:bb935622a668d4dc1cade90a1e637ea269bc4814012b5393f1c5cd436c6eb335","observation_id":"a49fed1b-915c-434b-b100-db8055b9e7aa","resolution":{"observed_at":"2026-08-03T09:21:40.391396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:40.493797Z","title":"Smart: Self-aware agent for tool overuse mitigation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.493797Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:d39e105761e0dd1cd3dfa2748aaed9dea92f21cd1d4d907f72a3dc5fbbf872a5","observation_id":"92669ec0-399b-4f0a-9ab2-448e7d6f5cb5","resolution":{"observed_at":"2026-08-03T09:21:40.493797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.05591","last_updated":"2025-04-09T09:09:37Z","snapshot_observed_at":"2026-08-06T04:47:05.686440Z","submitted_at":"2024-09-09T13:20:31Z","title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.05591","snapshot_observed_at":"2026-08-03T09:21:40.574746Z","title":"Memorag: Boosting long context processing with global memory-enhanced retrieval augmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.574746Z"},"links":{"cited_paper":"/paper/2409.05591","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:c4e304ce45f7b959f83edf3a86f525264d3f4b4d17521dcc338ff233f1d9e3b6","observation_id":"7821de4a-54f3-483d-a3ec-870de57808f6","resolution":{"observed_at":"2026-08-03T09:21:40.574746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:40.672071Z","title":"ToolLLM: Facilitating large language models to master 16000+ real-world APIs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.672071Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:dfa8057d16770059f9238ac39d41099b674c4deb5e17b5cdba48619e1af05324","observation_id":"65c2ee9d-384f-4318-b09b-0281d5b6ee5c","resolution":{"observed_at":"2026-08-03T09:21:40.672071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.20286","last_updated":"2025-05-26T17:58:53Z","snapshot_observed_at":"2026-08-07T15:21:20.945396Z","submitted_at":"2025-05-26T17:58:53Z","title":"Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.20286","snapshot_observed_at":"2026-08-03T09:21:40.747191Z","title":"Alita: Generalist agent enabling scalable agentic reasoning with minimal predefinition and maximal self-evolution.arXiv preprint arXiv:2505.20286, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.747191Z"},"links":{"cited_paper":"/paper/2505.20286","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:d953c4fd793ada189fb6a1e674860399e435e84274f5d20204af868ed5cb6bde","observation_id":"f4a8091b-7490-48a4-a116-ca3a25854629","resolution":{"observed_at":"2026-08-03T09:21:40.747191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:40.830363Z","title":"From exploration to mastery: Enabling llms to master tools via self-driven interactions","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.830363Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:931dd1ad4d7e3e691fe62a9eeee61dfa33062325b3dc3596a291e3a33a790b62","observation_id":"a4957c9b-c3b2-428b-aa15-5033655b354d","resolution":{"observed_at":"2026-08-03T09:21:40.830363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:21:40.905789Z","title":"A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond.arXiv preprint arXiv:2503.21614, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.905789Z"},"links":{"citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:4cd589b100c66b1e257afe847c45294a4b5e693679af15d83e9406c2d1f6f0ac","observation_id":"a3acf5bc-d0a8-43c8-aa9c-b65d59eb4c93","resolution":{"observed_at":"2026-08-03T09:21:40.905789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13956","last_updated":"2025-01-20T16:52:48Z","snapshot_observed_at":"2026-07-29T15:53:45.545304Z","submitted_at":"2025-01-20T16:52:48Z","title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.13956","snapshot_observed_at":"2026-08-03T09:21:40.959816Z","title":"Zep: a temporal knowledge graph architecture for agent memory.arXiv preprint arXiv:2501.13956, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:40.959816Z"},"links":{"cited_paper":"/paper/2501.13956","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:d8b8c1632d91007223b9d218e07b5a51aa96ea20a943681cc384c5c19b84a50d","observation_id":"5804efcf-94f1-4c6b-a5c3-1a8341b0d651","resolution":{"observed_at":"2026-08-03T09:21:40.959816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18279","last_updated":"2025-05-23T18:14:57Z","snapshot_observed_at":"2026-08-09T13:37:12.571934Z","submitted_at":"2025-05-23T18:14:57Z","title":"Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.18279","snapshot_observed_at":"2026-08-03T09:21:41.009387Z","title":"Collaborative memory: Multi-usermemorysharinginllmagentswithdynamicaccesscontrol.arXivpreprintarXiv:2505.18279, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-03T09:21:41.009387Z"},"links":{"cited_paper":"/paper/2505.18279","citing_paper":"/paper/2601.14192"},"observation_digest":"sha256:0a491f35d4bd2c82f2fb3ccc6bb162a10cd8f190c01156304f3f8e77c9e60009","observation_id":"ae64c634-6a93-468d-b8dc-e4f311d065f6","resolution":{"observed_at":"2026-08-03T09:21:41.009387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T15:05:40.772054Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":100,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":209},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 100 of 209 outbound references and 11 inbound Pith citation observations for arXiv:2601.14192."}