{"as_of":"2026-08-11T12:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:75d0013ee1c21b8f169f1ca941c566b9b42e018152414553f3988d67ea8478ec","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T14:06:43.714455Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T01:12:34.009288Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.14477","snapshot_observed_at":"2026-08-04T01:12:34.009288Z","title":"Test-time learning with an evolving library.arXiv preprint arXiv:2605.14477, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.00155","last_updated":"2026-07-31T17:50:08Z","snapshot_observed_at":"2026-08-07T23:09:41.455316Z","submitted_at":"2026-07-31T17:50:08Z","title":"AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T01:12:34.009288Z"},"links":{"cited_paper":"/paper/2605.14477","citing_paper":"/paper/2608.00155"},"observation_digest":"sha256:6e069ac6d3aa27fa8e9b86cd94093d5aecee8a41d1dc0da6237924733099fa61","observation_id":"b01a108e-71ff-4206-a9bc-190f1a4e571e","resolution":{"observed_at":"2026-08-04T01:12:34.009288Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.14477/citation-record","integrity":"/paper/2605.14477/integrity","json":"/paper/2605.14477/citation-record.json","paper":"/paper/2605.14477"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:06:39.906001Z","title":"Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:39.906001Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:f9a2064740416199f57e78e5e93ee934d60cc0ce65f2cc328f87546dcda07da7","observation_id":"9f308c0c-3423-45d3-ac93-588f441b4924","resolution":{"observed_at":"2026-08-02T14:06:39.906001Z","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":"2026-08-02T14:06:40.044889Z","title":"Large language models are better reasoners with self-verification","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.044889Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:644895678e482cd582fe923e9fa89857f1075e5844c3617a74db9342485c1587","observation_id":"bdeb3aed-eea5-4a84-96e9-8203bbc60b4c","resolution":{"observed_at":"2026-08-02T14:06:40.044889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03314","last_updated":"2024-08-06T17:35:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-06T17:35:05Z","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03314","snapshot_observed_at":"2026-08-02T14:06:40.223730Z","title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters.arXiv preprint arXiv:2408.03314, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.223730Z"},"links":{"cited_paper":"/paper/2408.03314","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:da94784b100486b95732743425f4f42174dce138a771d069e02b5e7ec7d9fa83","observation_id":"f62175bf-1672-447d-b8ee-bf0cce58495b","resolution":{"observed_at":"2026-08-02T14:06:40.223730Z","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":"2026-08-02T14:06:40.368807Z","title":"Test-time recursive thinking: Self-improvement without external feedback.arXiv preprint arXiv:2602.03094, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.368807Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:f5fbc3fd9db21898467972a019543e3897a075883a4459a70aa14abd7bd84b57","observation_id":"b5610af5-1758-4bf8-b9cf-e715c85ada39","resolution":{"observed_at":"2026-08-02T14:06:40.368807Z","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":"2026-08-02T14:06:40.512017Z","title":"s1: Simple test-time scaling","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.512017Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:5cc9afdac668fe5df2a1e37e08a4d3a2317270ba561a286810be5651486ed5ee","observation_id":"66aa346a-37bc-4329-8880-2a8b4c6f5bcf","resolution":{"observed_at":"2026-08-02T14:06:40.512017Z","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":"2026-08-02T14:06:40.627848Z","title":"Recursive self-aggregation unlocks deep thinking in large language models.arXiv preprint arXiv:2509.26626, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.627848Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:b761d852bfed45e35c500bdb04525c8b7b4018faa796e5c9a8f87ced82b97133","observation_id":"6c1fef70-55fd-45c0-a85d-1fd285584f77","resolution":{"observed_at":"2026-08-02T14:06:40.627848Z","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":"2026-08-02T14:06:40.715248Z","title":"Memory-assisted prompt editing to improve GPT-3 after deployment","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.715248Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:217daa9b634aacf0689df6128549cfa44ce71fe9fe61f0123e2af25ccd9a96ea","observation_id":"41bfad03-bf5d-4557-8d1e-9fb079a5c35f","resolution":{"observed_at":"2026-08-02T14:06:40.715248Z","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":"2026-08-02T14:06:40.817486Z","title":"Thought-retriever: Don’t just retrieve raw data, retrieve thoughts, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.817486Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:0d7d56496862cc007db73cdffb8fbcd8e3e771eec3c376657f2325c6c5496bb2","observation_id":"8d318405-ab71-4daa-ad4a-0bac117bb4fb","resolution":{"observed_at":"2026-08-02T14:06:40.817486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.20857","last_updated":"2026-05-18T16:18:02Z","snapshot_observed_at":"2026-08-11T09:44:01.811561Z","submitted_at":"2025-11-25T21:08:07Z","title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.20857","snapshot_observed_at":"2026-08-02T14:06:40.867144Z","title":"Evo-memory: Benchmarking llm agent test-time learning with self-evolving memory.arXiv preprint arXiv:2511.20857, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.867144Z"},"links":{"cited_paper":"/paper/2511.20857","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:307affa4a6909be480e139949dee795e49b30f63174304ab63ea0698350a68ca","observation_id":"c86321c1-05b6-446c-b9e4-48b35335e3cb","resolution":{"observed_at":"2026-08-02T14:06:40.867144Z","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":"2026-08-02T14:06:40.935712Z","title":"Test-time learning for large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:40.935712Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:e503f04c5b3a8a51493e71d4228d61dd19b3c0a281c0372bbfd4ab18cfae2a75","observation_id":"d95828d2-97ea-4b28-9eba-97a6eb40e56a","resolution":{"observed_at":"2026-08-02T14:06:40.935712Z","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":"2026-08-02T14:06:41.037640Z","title":"The surprising effectiveness of test-time training for few-shot learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.037640Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:c0d6c17ff72b711d054e63163c55b723ca18789413bb088b88280ea8196023b0","observation_id":"3e65ae77-6fcb-4813-8a7d-f491b8d6dda4","resolution":{"observed_at":"2026-08-02T14:06:41.037640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.16175","last_updated":"2026-02-05T18:03:03Z","snapshot_observed_at":"2026-08-01T10:41:29.420510Z","submitted_at":"2026-01-22T18:24:00Z","title":"Learning to Discover at Test Time","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.16175","snapshot_observed_at":"2026-08-02T14:06:41.118386Z","title":"Learning to discover at test time.arXiv preprint arXiv:2601.16175, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.118386Z"},"links":{"cited_paper":"/paper/2601.16175","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:821ec1ae5721b74b34c6024f9671a7626eae1c5e11c05b2b88c78fba6f6e5940","observation_id":"6678fbe8-8102-4e3c-99ce-5b1a94431c34","resolution":{"observed_at":"2026-08-02T14:06:41.118386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04620","last_updated":"2025-08-31T18:32:59Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-05T16:23:20Z","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04620","snapshot_observed_at":"2026-08-02T14:06:41.256749Z","title":"Learning to (learn at test time): Rnns with expressive hidden states","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.256749Z"},"links":{"cited_paper":"/paper/2407.04620","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:74d9158567347a5e4196fb12b31f2f646007e10141be3b36bef4c12204b5cc07","observation_id":"69dd0c2a-25c4-4be6-8061-22012f7aa830","resolution":{"observed_at":"2026-08-02T14:06:41.256749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.13875","last_updated":"2026-05-29T15:58:18Z","snapshot_observed_at":"2026-08-07T17:36:59.885812Z","submitted_at":"2026-03-14T10:17:33Z","title":"GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.13875","snapshot_observed_at":"2026-08-02T14:06:41.407457Z","title":"Gradmem: Learning to write context into memory with test-time gradient descent.arXiv preprint arXiv:2603.13875, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.407457Z"},"links":{"cited_paper":"/paper/2603.13875","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:8ad858f897425c77f8c92e82a54490c56ebb1e9e44fb994337499dea373ca5d5","observation_id":"61485b8c-b842-402c-8d17-1086be51ef7e","resolution":{"observed_at":"2026-08-02T14:06:41.407457Z","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":"2026-08-02T14:06:41.491642Z","title":"How to grow a mind: Statistics, structure, and abstraction.science, 331(6022):1279–1285, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.491642Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:589f79952bbea1385d8e98030a87d73c53f948d75e2be5c6ca1eeb156ec24519","observation_id":"66b586a8-13a3-4a57-9030-cd27f9675d40","resolution":{"observed_at":"2026-08-02T14:06:41.491642Z","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":"2026-08-02T14:06:41.606840Z","title":"Cognitive skill acquisition.Annual review of psychology, 47(1):513–539, 1996","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.606840Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:42c86c38735f247cc36765942d4fc26869cc40e46aa1697043e43ced7566e162","observation_id":"0aab9a1e-5b46-4368-905c-6a913603270f","resolution":{"observed_at":"2026-08-02T14:06:41.606840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.01547","last_updated":"2019-11-25T13:02:04Z","snapshot_observed_at":"2026-07-06T08:34:41.399203Z","submitted_at":"2019-11-05T00:31:38Z","title":"On the Measure of Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.01547","snapshot_observed_at":"2026-08-02T14:06:41.698667Z","title":"On the measure of intelligence.arXiv preprint arXiv:1911.01547, 2019","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.698667Z"},"links":{"cited_paper":"/paper/1911.01547","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:33c193e102de20d79dbfc6f4839092d3f9e2623c008c122d2d6c86cc3d3482bf","observation_id":"13c972b8-9e33-4c5f-8042-8ea67ed3e7c5","resolution":{"observed_at":"2026-08-02T14:06:41.698667Z","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":"2026-08-02T14:06:41.779448Z","title":"Walt: Web agents that learn tools.arXiv preprint arXiv:2510.01524, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.779448Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:94594500989e87377b0b7eb3b356ca34eb64c09823443aa33617bf702add16af","observation_id":"2f0422e7-45fc-44a2-b5da-9283d073cb30","resolution":{"observed_at":"2026-08-02T14:06:41.779448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.02268","last_updated":"2026-05-15T09:15:24Z","snapshot_observed_at":"2026-07-06T22:51:44.663367Z","submitted_at":"2026-04-02T17:03:05Z","title":"SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.02268","snapshot_observed_at":"2026-08-02T14:06:41.867863Z","title":"Skill0: In-context agentic reinforcement learning for skill internalization.arXiv preprint arXiv:2604.02268, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.867863Z"},"links":{"cited_paper":"/paper/2604.02268","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:7cbf32df9bd9a8e4c6978b26f2aa58227c0b49b6c2ab8ad869bd72f86dfac5a0","observation_id":"d4acbdb9-d1ec-43e1-a012-68f64ba67147","resolution":{"observed_at":"2026-08-02T14:06:41.867863Z","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":"2026-08-02T14:06:41.977220Z","title":"ReGAL: Refactoring programs to discover generalizable abstractions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:41.977220Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:2500f8d834c8b3a42e0cc6c063cb130e289822ae40d981d194c2fc76c1a02795","observation_id":"7f2b0703-6f92-49ac-9bc8-3a21f28b1eb0","resolution":{"observed_at":"2026-08-02T14:06:41.977220Z","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":"2026-08-02T14:06:42.064369Z","title":"Inducing programmatic skills for agentic tasks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.064369Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:0dbaae4b141aecf304911ecd6289a1c635001136fded29a8bc254cb73ae111d4","observation_id":"1dfd1a0f-d096-4d11-8500-bd85da9222c0","resolution":{"observed_at":"2026-08-02T14:06:42.064369Z","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":"2026-08-02T14:06:42.141475Z","title":"Reuseit: Synthesizing reusable ai agent workflows for web automation","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.141475Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:669f08580cce6a311c9595d691dbd0ece0e0731b3c8cde94052caeece9c20685","observation_id":"1e5c7116-3182-4284-b069-f8c5d11090e6","resolution":{"observed_at":"2026-08-02T14:06:42.141475Z","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":"2026-08-02T14:06:42.214953Z","title":"Autorefine: From trajectories to reusable expertise for continual llm agent refinement.arXiv preprint arXiv:2601.22758, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.214953Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:1163964f1bd60b358c8f675f11f41a517bc603011a90749c5a8d91fb2d6a7a16","observation_id":"a44c0df6-6f13-4fe4-8b22-79e5263430c1","resolution":{"observed_at":"2026-08-02T14:06:42.214953Z","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":"2026-08-02T14:06:42.280404Z","title":"Arcmemo: Abstract reasoning composition with lifelong llm memory.arXiv preprint arXiv:2509.04439, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.280404Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:fbdab0cdc558892affa418e9dde74f40becdbe292471208a9ddd981937695735","observation_id":"f37f4e19-6ff6-4f7e-83e6-8075ce091d75","resolution":{"observed_at":"2026-08-02T14:06:42.280404Z","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":"2026-08-02T14:06:42.321685Z","title":"Expel: Llm agents are experiential learners.Proceedings of the AAAI Conference on Artificial Intelligence, 38(17):19632– 19642, Mar","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.321685Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:de69258222d595e5478e7564fab126f666740e09cc834f71647d9e243eff6702","observation_id":"28fa7df7-b2a5-42d5-999d-0c7f756fb818","resolution":{"observed_at":"2026-08-02T14:06:42.321685Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.16079","last_updated":"2026-05-16T02:57:47Z","snapshot_observed_at":"2026-08-05T00:54:36.690304Z","submitted_at":"2025-10-17T12:03:16Z","title":"EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.16079","snapshot_observed_at":"2026-08-02T14:06:42.390142Z","title":"Evolver: Self-evolving llm agents through an experience-driven lifecycle.arXiv preprint arXiv:2510.16079, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.390142Z"},"links":{"cited_paper":"/paper/2510.16079","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:a2f9750aab1119a86957be8479678ec7dedaad72a11ee3fca00ff60ecf6fbbd8","observation_id":"eed35573-f7c9-4bd3-8ee2-b23eba27e74d","resolution":{"observed_at":"2026-08-02T14:06:42.390142Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.03509","last_updated":"2026-06-22T21:27:19Z","snapshot_observed_at":"2026-08-11T08:19:50.077867Z","submitted_at":"2026-01-07T01:43:25Z","title":"Evolving Programmatic Skill Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.03509","snapshot_observed_at":"2026-08-02T14:06:42.475660Z","title":"Evolving programmatic skill networks.arXiv preprint arXiv:2601.03509, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.475660Z"},"links":{"cited_paper":"/paper/2601.03509","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:60ca82f48c642e5269378cc312e82db36b008fc9081dea76cf8a735489190b48","observation_id":"3e7c9a7e-3b66-4292-a81b-12b5bcc7860d","resolution":{"observed_at":"2026-08-02T14:06:42.475660Z","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":"2026-08-02T14:06:42.576758Z","title":"Rlad: Training llms to discover abstractions for solving reasoning problems.arXiv preprint arXiv:2510.02263, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.576758Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:053048656b275f367e6ed41133d576c2e14ebaa46aab5d19b8e0977dde662dfb","observation_id":"8265c6c2-a1e2-4d71-81b7-0172acc179d3","resolution":{"observed_at":"2026-08-02T14:06:42.576758Z","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":"2026-08-02T14:06:42.648722Z","title":"Hybrid-gym: Training coding agents to generalize across tasks.arXiv preprint arXiv:2602.16819, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.648722Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:1e0bf0c3125594d463c3525b01bc9a3be6212faf1798ca0a357d53ad66192202","observation_id":"e4171741-679b-4565-b098-319a209186fa","resolution":{"observed_at":"2026-08-02T14:06:42.648722Z","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":"2026-08-02T14:06:42.719043Z","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":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.719043Z"},"links":{"cited_paper":"/paper/2408.06292","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:b864496efe865f5f28ac769a2c5dd7173591409980d56b537b1f64105d40cc4e","observation_id":"da316eb5-fd42-46c0-bbd1-bed285613695","resolution":{"observed_at":"2026-08-02T14:06:42.719043Z","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":"2026-08-02T14:06:42.794639Z","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":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.794639Z"},"links":{"cited_paper":"/paper/2506.13131","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:80dc6557fe96d30a3aafab39e0678679f3218fffbe0a0fc805fd17655cbb0f53","observation_id":"c4f1a9aa-da23-4aa2-b808-d577e763fa13","resolution":{"observed_at":"2026-08-02T14:06:42.794639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.23473","last_updated":"2025-11-28T18:58:14Z","snapshot_observed_at":"2026-08-04T17:31:45.294646Z","submitted_at":"2025-11-28T18:58:14Z","title":"ThetaEvolve: Test-time Learning on Open Problems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.23473","snapshot_observed_at":"2026-08-02T14:06:42.860461Z","title":"Thetaevolve: Test-time learning on open problems.arXiv preprint arXiv:2511.23473, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.860461Z"},"links":{"cited_paper":"/paper/2511.23473","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:67e9511c658f66108fb9091db620f5a8b0fb672b50adeb3277d9006d8f9f074b","observation_id":"2de8f593-e5c3-4756-bef6-4561b0b13710","resolution":{"observed_at":"2026-08-02T14:06:42.860461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.08377","last_updated":"2026-08-10T11:40:00Z","snapshot_observed_at":"2026-08-11T11:24:27.856756Z","submitted_at":"2026-04-09T15:38:27Z","title":"SkillClaw: Let Skills Evolve Collectively with Agentic Evolver","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.08377","snapshot_observed_at":"2026-08-02T14:06:42.931355Z","title":"Skillclaw: Let skills evolve collectively with agentic evolver.arXiv preprint arXiv:2604.08377, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.931355Z"},"links":{"cited_paper":"/paper/2604.08377","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:fa43ffa077fe13180e8c2ebb5416912c45ee4fd7463878d0b0ff75b7b526a946","observation_id":"c97fa7df-c697-4271-a3eb-6355797b4f0b","resolution":{"observed_at":"2026-08-02T14:06:42.931355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.02766","last_updated":"2026-03-03T09:07:22Z","snapshot_observed_at":"2026-08-04T19:32:12.955430Z","submitted_at":"2026-03-03T09:07:22Z","title":"EvoSkill: Automated Skill Discovery for Multi-Agent Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.02766","snapshot_observed_at":"2026-08-02T14:06:42.989712Z","title":"Evoskill: Automated skill discovery for multi-agent systems.arXiv preprint arXiv:2603.02766, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:42.989712Z"},"links":{"cited_paper":"/paper/2603.02766","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:af73c177be799eae196c3dd1ddc0f9053217c681580b0a63f687662b5623f1fd","observation_id":"7084175f-e9ad-4322-a3b1-08b18b0ac107","resolution":{"observed_at":"2026-08-02T14:06:42.989712Z","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":"2026-08-02T14:06:43.075003Z","title":"Agent workflow memory","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.075003Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:0307b31c25ad799984cc9d1c6f9310b214d755c44651f9139a679385b9fe58b4","observation_id":"7807b759-cc97-40b4-9a57-9677fe9e3e73","resolution":{"observed_at":"2026-08-02T14:06:43.075003Z","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":"2026-08-02T14:06:43.114521Z","title":"Dynamic cheatsheet: Test-time learning with adaptive memory","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.114521Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:64e75931afd6cf7ff3517815b445e91fa3bf06e568aa671f754fa01d528b066d","observation_id":"4a97aa4c-a337-45d5-a615-6971c7e870f8","resolution":{"observed_at":"2026-08-02T14:06:43.114521Z","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":"2026-08-02T14:06:43.183496Z","title":"Reasoningbank: Scaling agent self-evolving with reasoning memory","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.183496Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:2749292334d8c7652d809f73e3e6bda4ff8fe877192bcfc78d696cb2221d57a0","observation_id":"744b2df5-2438-4dc4-8636-2adb22d4e9ca","resolution":{"observed_at":"2026-08-02T14:06:43.183496Z","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":"2026-08-02T14:06:43.240451Z","title":"Judging llm-as-a- judge with mt-bench and chatbot arena","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.240451Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:69f1565a4b097849ac52dcd2aa42a1e41c9d8a7c183322fd1485adf6c80b857e","observation_id":"902ddd6b-ef6f-4a78-818a-a12feb819bb7","resolution":{"observed_at":"2026-08-02T14:06:43.240451Z","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":"2026-08-02T14:06:43.295412Z","title":"Bigcodebench: Benchmarking code generation with diverse function calls and complex instructions","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.295412Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:2eda009bfd31bb6f82e74ac7769be32817fda19838b014d28c68839d189df23d","observation_id":"8bc54f3d-314a-482f-a77d-c8b14414f810","resolution":{"observed_at":"2026-08-02T14:06:43.295412Z","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":"2026-08-02T14:06:43.345294Z","title":"Livecodebench: Holistic and contamination free evaluation of large language models for code","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.345294Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:7ab659d2e850677e2cf463a269eaa78eb8af09027633f0ea39815727e8cbb4fd","observation_id":"5319b7f2-c8ab-4e65-a7b2-80e4b9a9a04a","resolution":{"observed_at":"2026-08-02T14:06:43.345294Z","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":"2026-08-02T14:06:43.385394Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.385394Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:6ec8e53794d2ee48045483708f7d2a5595162219bace0587a2f07bb12ab523e8","observation_id":"a41c7dc8-6753-476f-b5c5-42ed9e80da6c","resolution":{"observed_at":"2026-08-02T14:06:43.385394Z","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":"2026-08-02T14:06:43.463200Z","title":"The 2014 international planning competition: Progress and trends.Ai Magazine, 36(3):90–98, 2015","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.463200Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:e65f4187a77fc1a599335ccaf2029562e2c0ca381518d3fab1e9ed2528863ee7","observation_id":"35ad20e4-7d64-4a49-8ca2-43bfd74f32b3","resolution":{"observed_at":"2026-08-02T14:06:43.463200Z","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":"2026-08-02T14:06:43.586725Z","title":"Agentboard: An analytical evaluation board of multi-turn llm agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.586725Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:fa35bd6fe2056cd2c70dfc2f6a35137d2e79e28a862de485c59c965f3fa55349","observation_id":"3a6dbba4-bc9f-44a3-a8d3-71dff2883d90","resolution":{"observed_at":"2026-08-02T14:06:43.586725Z","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":"2026-08-02T14:06:43.664147Z","title":"Matharena: Evaluating llms on uncontaminated math competitions.Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmark, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.664147Z"},"links":{"citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:c0521d693a6407543b4a517a36492696fc81b2d08985e2966256d8d8b11bc684","observation_id":"1c19b931-8ccb-490e-8d23-c029090d1b5a","resolution":{"observed_at":"2026-08-02T14:06:43.664147Z","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":"2026-08-02T14:06:43.714455Z","title":"Limitations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T14:06:43.714455Z"},"links":{"cited_paper":"/paper/2410.21276","citing_paper":"/paper/2605.14477"},"observation_digest":"sha256:3fce7e31b15ac1fb32c8f7481945046fcf72590d70d98ff404d8e569919fcc5f","observation_id":"96a2caae-5b8e-4a7b-9cb2-49e580dcaa89","resolution":{"observed_at":"2026-08-02T14:06:43.714455Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.14477","last_updated":"2026-07-14T21:30:34Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T14:06:39.249902Z","submitted_at":"2026-05-14T07:18:12Z","title":"Test-Time Learning with an Evolving Library"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":44,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":45},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2605.14477."}