{"as_of":"2026-08-17T14:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c29ef24df6a0dde8bdade576e2a5369ee4ede5ef2d6d7f5e9f739e9a7240b183","coverage":[{"denominator":92,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":92,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T00:46:12.985114Z","state":"measured"},{"denominator":92,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":92,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"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":[],"links":{"evidence":"/evidence","html":"/paper/2607.27443/citation-record","integrity":"/paper/2607.27443/integrity","json":"/paper/2607.27443/citation-record.json","paper":"/paper/2607.27443"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T00:46:08.617285Z","title":"Graph of thoughts: Solving elaborate problems with large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:08.617285Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:b58119545ec79799c933e5ce8e3107530c07035b5668004114f5e58f6b42fef6","observation_id":"b0668d78-5cb6-4e6c-a4aa-98c51df35f78","resolution":{"observed_at":"2026-07-31T00:46:08.617285Z","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":"2026-07-31T00:46:08.675104Z","title":"O’Reilly Media, Inc., 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:08.675104Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:7f9166acf2340a71aa011df3f747addcf15ed4b7229362257187abb2ea981de8","observation_id":"05c6b53f-e4b1-4663-8a3c-4b0b0325e661","resolution":{"observed_at":"2026-07-31T00:46:08.675104Z","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":"2026-07-31T00:46:08.734655Z","title":"Springer, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:08.734655Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:d8755719efd4d2ce12c0cc7a348d717396e5aed9f697122fc9dbe7c72c2bd172","observation_id":"ecfd69c8-3522-4618-90d1-e160bf81084c","resolution":{"observed_at":"2026-07-31T00:46:08.734655Z","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":"2026-07-31T00:46:08.775827Z","title":"Grounding large language models in interactive environments with online reinforcement learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:08.775827Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:ac263c45fc447b38ae0a8ac8374d7130e68dbff3855ea06538ea54fe53ca0772","observation_id":"413de852-5dd9-4b3e-944c-186b657c1681","resolution":{"observed_at":"2026-07-31T00:46:08.775827Z","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":"2026-07-31T00:46:08.823676Z","title":"Agentboard: An analytical evaluation board of multi-turn llm agents.Advances in neural information processing systems, 37:74325–74362, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:08.823676Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:81bb2d981eb378f3633af946ce431954897925a7b96b9d9f83f740d597f0bb32","observation_id":"dd65b6dd-7c75-4cfe-b8e5-68ce58930710","resolution":{"observed_at":"2026-07-31T00:46:08.823676Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05915","last_updated":"2023-10-09T17:58:38Z","snapshot_observed_at":"2026-08-16T14:53:43.494263Z","submitted_at":"2023-10-09T17:58:38Z","title":"FireAct: Toward Language Agent Fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05915","snapshot_observed_at":"2026-07-31T00:46:08.879772Z","title":"Fireact: Toward language agent fine-tuning.arXiv preprint arXiv:2310.05915, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:08.879772Z"},"links":{"cited_paper":"/paper/2310.05915","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:cf133837f5f49f745733e0766a455854eb67282296f21589970f41dab50ec68b","observation_id":"b35807e4-fae5-419d-a086-825e7bb85ae3","resolution":{"observed_at":"2026-07-31T00:46:08.879772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15649","last_updated":"2024-09-13T09:36:18Z","snapshot_observed_at":"2026-08-16T14:40:09.261191Z","submitted_at":"2023-11-27T09:20:23Z","title":"RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15649","snapshot_observed_at":"2026-07-31T00:46:08.937449Z","title":"Robogpt: an intelligent agent of making embodied long-term decisions for daily instruction tasks.arXiv preprint arXiv:2311.15649, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:08.937449Z"},"links":{"cited_paper":"/paper/2311.15649","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:c48c860bdaa63f273f89b24e607da482d1268c58146ac6e4dbc719c56ea7627b","observation_id":"c529326f-0192-4fc6-b058-0c044d128190","resolution":{"observed_at":"2026-07-31T00:46:08.937449Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.11532","last_updated":"2019-11-08T14:57:21Z","snapshot_observed_at":"2026-08-14T18:57:26.454752Z","submitted_at":"2018-06-29T16:56:07Z","title":"TextWorld: A Learning Environment for Text-based Games","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.11532","snapshot_observed_at":"2026-07-31T00:46:08.985209Z","title":"Textworld: A learning environment for text-based games.CoRR, abs/1806.11532, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:08.985209Z"},"links":{"cited_paper":"/paper/1806.11532","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:fac7a75408a4274f18b52e1136e243fe9da219a0c4fd9e56086316589e3fcbe3","observation_id":"64606010-e5de-44e6-809b-3556882f7cb9","resolution":{"observed_at":"2026-07-31T00:46:08.985209Z","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":"2026-07-31T00:46:09.038610Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.038610Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:c6dab8fd90c5591a25b026a34c913af3d616285acb22d43e84d714109b131fa7","observation_id":"996a1a99-765f-409c-87c1-fb249199968a","resolution":{"observed_at":"2026-07-31T00:46:09.038610Z","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":"2026-07-31T00:46:09.101507Z","title":"Retrieval augmented language model pre-training","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.101507Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:1d75b822e19024b15cae6fc69cf7f467ea4c76b3600b8a95d9b9bb8de91620d0","observation_id":"0357104b-5b14-4e46-ab71-87fc5a8c289d","resolution":{"observed_at":"2026-07-31T00:46:09.101507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14992","last_updated":"2023-10-23T07:24:28Z","snapshot_observed_at":"2026-08-15T11:39:07.998070Z","submitted_at":"2023-05-24T10:28:28Z","title":"Reasoning with Language Model is Planning with World Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14992","snapshot_observed_at":"2026-07-31T00:46:09.125807Z","title":"Reasoning with language model is planning with world model.arXiv preprint arXiv:2305.14992, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.125807Z"},"links":{"cited_paper":"/paper/2305.14992","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:546ea8c73cf9171a6e824c68a390bbd04563248b91a56349fb295c0efdde7add","observation_id":"b72044fc-8636-43c2-86e9-d31431f133aa","resolution":{"observed_at":"2026-07-31T00:46:09.125807Z","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":"2026-07-31T00:46:09.194309Z","title":"Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.194309Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:306e21ea0bfdb50623131e06598e3019bde6a11fb06c9aa18ec5ef9288306d2d","observation_id":"f4d5b2fd-3a89-432b-aadc-0f5356039c75","resolution":{"observed_at":"2026-07-31T00:46:09.194309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.11403","last_updated":"2024-05-18T22:10:15Z","snapshot_observed_at":"2026-08-16T13:51:36.604031Z","submitted_at":"2024-05-18T22:10:15Z","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.11403","snapshot_observed_at":"2026-07-31T00:46:09.244245Z","title":"Mapcoder: Multi-agent code generation for competitive problem solving.arXiv preprint arXiv:2405.11403, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.244245Z"},"links":{"cited_paper":"/paper/2405.11403","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:0ee27ed0a0850c05aa394996798780abcbcab16da0ec7fbe0ec5f5af722bcaee","observation_id":"ae571369-7a89-4cae-80ea-7c19a657f653","resolution":{"observed_at":"2026-07-31T00:46:09.244245Z","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":"2026-07-31T00:46:09.293774Z","title":"Jansen and Marc-Alexandre Côté","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.293774Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:45ba6888a2dbf49c86c9c4850a0be867061a426b900289e2523294e9e6053606","observation_id":"eb4a9f3d-bf21-463e-8651-d8e83dbc14c9","resolution":{"observed_at":"2026-07-31T00:46:09.293774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03610","last_updated":"2024-02-06T00:53:27Z","snapshot_observed_at":"2026-08-16T14:21:12.027923Z","submitted_at":"2024-02-06T00:53:27Z","title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03610","snapshot_observed_at":"2026-07-31T00:46:09.346973Z","title":"Rap: Retrieval-augmented planning with contextual memory for multimodal llm agents.arXiv preprint arXiv:2402.03610, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.346973Z"},"links":{"cited_paper":"/paper/2402.03610","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:c49d3c4a1350991a47c21adb72f1134abc527fcde05053b48a9895c4ff3c74fe","observation_id":"a93c2c59-dcb5-45a9-a050-6d73cfd45cae","resolution":{"observed_at":"2026-07-31T00:46:09.346973Z","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":"2026-07-31T00:46:09.405398Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.405398Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:761c4a8c6ed386f01895310d6fca05238dfcbc9cdd6dd7c71f592e34045f3005","observation_id":"06427f5b-ab11-40c2-85cc-fd8b9ab60d28","resolution":{"observed_at":"2026-07-31T00:46:09.405398Z","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":"2026-07-31T00:46:09.453243Z","title":"The MIT Press, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.453243Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:b9a26673010cb3bad0e5e97dd22125eceb8896ac4e70110926503577b26d5cad","observation_id":"2023338c-0bbf-413e-ac03-767e990214c7","resolution":{"observed_at":"2026-07-31T00:46:09.453243Z","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":"2026-07-31T00:46:09.502695Z","title":"Complex knowledge base question answering: A survey.IEEE Transactions on Knowledge and Data Engineering, 35(11):11196–11215, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.502695Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:0f09a4293726e83358cf6121f1a4daf1d490eee266424af2f13ee4403af93b02","observation_id":"b800f9e0-ecca-4469-a666-dbb90158c4c2","resolution":{"observed_at":"2026-07-31T00:46:09.502695Z","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":"2026-07-31T00:46:09.564964Z","title":"Dhrl: A graph-based approach for long-horizon and sparse hierarchical reinforcement learning.Advances in Neural Information Processing Systems, 35:13668–13678, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.564964Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:5a3361475f13644e1f5c735bef79f470153cf1e375e39744ff348aac118ffc08","observation_id":"1e0c512d-58a2-4437-a252-e7577ab94059","resolution":{"observed_at":"2026-07-31T00:46:09.564964Z","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":"2026-07-31T00:46:09.619502Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.619502Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:ea5c9a923c778456ff00c606a9ffde79827c42b828b20dc641665c606d202a31","observation_id":"f76233e0-73dc-43ce-97c6-402607d36700","resolution":{"observed_at":"2026-07-31T00:46:09.619502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.18415","last_updated":"2024-10-24T04:01:40Z","snapshot_observed_at":"2026-08-16T13:06:25.266212Z","submitted_at":"2024-10-24T04:01:40Z","title":"Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.18415","snapshot_observed_at":"2026-07-31T00:46:09.667670Z","title":"Decoding on graphs: Faithful and sound reasoning on knowledge graphs through generation of well-formed chains.arXiv preprint arXiv:2410.18415, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.667670Z"},"links":{"cited_paper":"/paper/2410.18415","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:8faf38d3e21a22b981f711d46753209fb563eb28253e26087194ef084ec9f759","observation_id":"12f80f25-cfe8-4e07-831c-78ad0d3957b8","resolution":{"observed_at":"2026-07-31T00:46:09.667670Z","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":"2026-07-31T00:46:09.753658Z","title":"Embodied agent interface: Benchmarking llms for embodied decision making.Advances in Neural Information Processing Systems, 37:100428–100534, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.753658Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:34cd5ed9a9d094c3cbd6fa1bce5c140c910e5289f131f16d473103fc130838e0","observation_id":"21a6ad3e-4eef-4ca3-bcc6-800cbc4ab567","resolution":{"observed_at":"2026-07-31T00:46:09.753658Z","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":"2026-07-31T00:46:09.803011Z","title":"A survey on text classification: From traditional to deep learning.ACM Transactions on Intelligent Systems and Technology (TIST), 13(2):1–41, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.803011Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:7004c2fb01fd2a7f53a2480d7552e72613723da72d8b777d837644177dd2df54","observation_id":"441edc4a-2a98-4a3c-a2e9-c39e631f6040","resolution":{"observed_at":"2026-07-31T00:46:09.803011Z","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":"2026-07-31T00:46:09.895126Z","title":"Pre-trained language models for interactive decision-making.Advances in Neural Information Processing Systems, 35:31199–31212, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.895126Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:72a9f05a564c8d562aa393cca7f8f9b44c173d98d019465b1484172ddca05d87","observation_id":"397a35ce-c551-4d3a-8184-9b6e7ee7b276","resolution":{"observed_at":"2026-07-31T00:46:09.895126Z","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":"2026-07-31T00:46:09.966412Z","title":"Injecting structured knowledge into llms via graph neural networks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:09.966412Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:62d09bbfef28216a983ec0311871c2dfb138f47131d3a8802f263199dfd9ab2b","observation_id":"e2975ba7-78c0-4549-8010-83250ce94396","resolution":{"observed_at":"2026-07-31T00:46:09.966412Z","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":"2026-07-31T00:46:10.010678Z","title":"Prompt compression with context-aware sentence encoding for fast and improved llm inference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.010678Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:9a8025f1db328a79c25454adf07b85dc4dcc6b10a6a6ed87673f6b0dd6786195","observation_id":"e5b3ea18-45d5-4fe8-9f64-e6632250e98b","resolution":{"observed_at":"2026-07-31T00:46:10.010678Z","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":"2026-07-31T00:46:10.083017Z","title":"Fairness and bias in robot learning.Proceedings of the IEEE, 112(4):305–330, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.083017Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:f6035234911db2517677cf63c4226ebad374ad767ab736f757f82590975495cc","observation_id":"e4097d5f-0d7a-4c77-a0b7-aa503c122e6f","resolution":{"observed_at":"2026-07-31T00:46:10.083017Z","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":"2026-07-31T00:46:10.164785Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.164785Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:6c90ac6dc1b12e91246324d912f75b6a07d43bb0e89d4bfb3ad598defde47cea","observation_id":"f54f555c-b183-4d02-9f5f-75def80e868d","resolution":{"observed_at":"2026-07-31T00:46:10.164785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13080","last_updated":"2025-05-28T04:54:26Z","snapshot_observed_at":"2026-08-16T13:08:37.238056Z","submitted_at":"2024-10-16T22:55:17Z","title":"Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13080","snapshot_observed_at":"2026-07-31T00:46:10.300143Z","title":"Graph-constrained reasoning: Faithful reasoning on knowledge graphs with large language models.arXiv preprint arXiv:2410.13080, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.300143Z"},"links":{"cited_paper":"/paper/2410.13080","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:a9750fe4e7c3a229fb3f7c6578f0ed645eb1f88752d2c7aa9a453b0428eb2a3c","observation_id":"ebe0af0c-e496-4d16-be25-08b991c10c08","resolution":{"observed_at":"2026-07-31T00:46:10.300143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14093","last_updated":"2026-05-01T01:50:44Z","snapshot_observed_at":"2026-08-04T06:47:25.827167Z","submitted_at":"2024-05-23T01:43:54Z","title":"A Survey on Vision-Language-Action Models for Embodied AI","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14093","snapshot_observed_at":"2026-07-31T00:46:10.419134Z","title":"A survey on vision- language-action models for embodied ai.arXiv preprint arXiv:2405.14093, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.419134Z"},"links":{"cited_paper":"/paper/2405.14093","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:a37e3c00a7ed429adcddc0e30025f1d9409709b923c3c2f2a5b7cd7f7ddd35b4","observation_id":"362b3043-2009-4ee6-9104-28427bfe0db0","resolution":{"observed_at":"2026-07-31T00:46:10.419134Z","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":"2026-07-31T00:46:10.502096Z","title":"Gnn-rag: Graph neural retrieval for efficient large lan- guage model reasoning on knowledge graphs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.502096Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:4b739d5d2987b3c70dc0a11eac3b6b5fbc0ae9bf5fd84ea49089414f1373fd97","observation_id":"1ad1fd9e-fbd3-40b9-a951-1f163e3aa955","resolution":{"observed_at":"2026-07-31T00:46:10.502096Z","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":"2026-07-31T00:46:10.638118Z","title":"Large dual encoders are generalizable retrievers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.638118Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:6770da3bd5838d2d9882052b1e8bcf8ab35f52d8996255f61ad78592b81c4689","observation_id":"c6f3e680-c8a7-4e07-a029-707485755d8d","resolution":{"observed_at":"2026-07-31T00:46:10.638118Z","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":"2026-07-31T00:46:10.768470Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.768470Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:819e65780ca2db32f7809408ebdd7e83ef6c59558eec98e45f13fad717c583d1","observation_id":"bce4e191-fc0f-450f-9fcd-9cb3f5bf9ea8","resolution":{"observed_at":"2026-07-31T00:46:10.768470Z","resolver_source":null,"status":"parse_uncertain"},"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":"2026-07-31T00:46:10.840775Z","title":"Gpt-4o mini: advancing cost-efficient intelligence","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.840775Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:b2346c7883fbbda5caec9727d0fa2a2e5341c30aeb332068258fb77f954db5cf","observation_id":"a90a5198-0975-49aa-9598-5437ea057622","resolution":{"observed_at":"2026-07-31T00:46:10.840775Z","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":"2026-07-31T00:46:10.904493Z","title":"Graphical models for probabilistic and causal reasoning.Quantified representation of uncertainty and imprecision, pages 367–389, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.904493Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:cc824ea9808020454e620670dfe5319653abe03b0ee4e3e7fb762e3ace7cad56","observation_id":"2c0f5780-a1bf-448a-9849-2a1d55c5a2c7","resolution":{"observed_at":"2026-07-31T00:46:10.904493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08921","last_updated":"2024-09-10T15:38:56Z","snapshot_observed_at":"2026-08-16T13:26:16.333766Z","submitted_at":"2024-08-15T12:20:24Z","title":"Graph Retrieval-Augmented Generation: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.08921","snapshot_observed_at":"2026-07-31T00:46:10.925769Z","title":"Graph retrieval-augmented generation: A survey.arXiv preprint arXiv:2408.08921, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.925769Z"},"links":{"cited_paper":"/paper/2408.08921","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:e78decfeab1034569bab4ad6fc7a24af0cec1e74c7823c6c5263e699e7896ac8","observation_id":"14c6829d-3bf1-4840-99d0-98c22751c374","resolution":{"observed_at":"2026-07-31T00:46:10.925769Z","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":"2026-07-31T00:46:10.973102Z","title":"Virtualhome: Simulating household activities via programs","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:10.973102Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:2e7a01e2326c91acb775d10a59427b23ccc4fda609c980c4dba5d57574ed6b79","observation_id":"a1069f18-4ccd-4bf0-8042-293fb1d2c909","resolution":{"observed_at":"2026-07-31T00:46:10.973102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.07924","last_updated":"2024-06-05T13:23:49Z","snapshot_observed_at":"2026-08-16T00:37:44.307785Z","submitted_at":"2023-07-16T02:11:34Z","title":"ChatDev: Communicative Agents for Software Development","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.07924","snapshot_observed_at":"2026-07-31T00:46:11.035645Z","title":"Chatdev: Communicative agents for software development","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.035645Z"},"links":{"cited_paper":"/paper/2307.07924","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:b1941b47cb1a6a4e941b1bf0356c9ee810b0ea28bb0faafeb50b660275edea53","observation_id":"379b6f61-1a54-4ad1-8679-7c1197acab34","resolution":{"observed_at":"2026-07-31T00:46:11.035645Z","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":"2026-07-31T00:46:11.062990Z","title":"Term-weighting approaches in automatic text retrieval","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.062990Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:88c107863d178bc508f14d2c109d3ca5e262d951b81075d92fef7ef36f113a75","observation_id":"83849795-05d8-4bd9-b040-6ab1e573e8b1","resolution":{"observed_at":"2026-07-31T00:46:11.062990Z","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":"2026-07-31T00:46:11.132352Z","title":"Reflex- ion: language agents with verbal reinforcement learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.132352Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:bd1577afbed347aaef8d30bd7055ed8e7b05fe1cc60461d04a4af1d53a4870f0","observation_id":"d84b7e9f-a466-4655-b4bb-bcf42e1e86d8","resolution":{"observed_at":"2026-07-31T00:46:11.132352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03768","last_updated":"2021-03-14T22:44:38Z","snapshot_observed_at":"2026-08-13T15:27:25.430393Z","submitted_at":"2020-10-08T05:13:36Z","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03768","snapshot_observed_at":"2026-07-31T00:46:11.174400Z","title":"Alfworld: Aligning text and embodied environments for interactive learning.arXiv preprint arXiv:2010.03768, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.174400Z"},"links":{"cited_paper":"/paper/2010.03768","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:c9d541492e252611c5a059dd8bc162dc3c990208871e31dd550cd5f4ef8e7450","observation_id":"bb1eea3d-1103-4289-a388-9e7467a667f2","resolution":{"observed_at":"2026-07-31T00:46:11.174400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-08-16T14:12:52.561838Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-07-31T00:46:11.219569Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents.arXiv preprint arXiv:2403.02502, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.219569Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:86ec35d3bf19fbca2aec669c3a11369ca4b40a88931233d012284ee7f5d9dcb9","observation_id":"e4d25527-dbe6-4bf0-8e64-2cf2c4db6b9d","resolution":{"observed_at":"2026-07-31T00:46:11.219569Z","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":"2026-07-31T00:46:11.266425Z","title":"MIT press Cambridge, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.266425Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:5e8939dade9d4dc2a5a93e12f2679d2d7c856008dec8957b163a34b473564b8d","observation_id":"dd93d7e7-97a0-499f-8716-0f5a8c9347a0","resolution":{"observed_at":"2026-07-31T00:46:11.266425Z","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":"2026-07-31T00:46:11.308992Z","title":"A comprehensive survey of text classification techniques and their research applications: Observational and experimental insights.Computer Science Review, 54:100664, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.308992Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:7c13d48a6140cc83b461abd1a1189c7dfbd52d37cc893599e8340cb8c66f04e3","observation_id":"62d181f2-d668-4032-8b09-a79f62d84232","resolution":{"observed_at":"2026-07-31T00:46:11.308992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05530","last_updated":"2024-12-16T17:39:39Z","snapshot_observed_at":"2026-08-14T18:15:53.516440Z","submitted_at":"2024-03-08T18:54:20Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05530","snapshot_observed_at":"2026-07-31T00:46:11.330926Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.arXiv preprint arXiv:2403.05530, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.330926Z"},"links":{"cited_paper":"/paper/2403.05530","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:1f730cac7cc91ee853ea4fcd3ef34f43cb9eb51a044af9887d1f98a327884156","observation_id":"faf3d9dd-6420-4788-9c5d-74c0159b9c7c","resolution":{"observed_at":"2026-07-31T00:46:11.330926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19786","last_updated":"2025-03-25T15:52:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-25T15:52:34Z","title":"Gemma 3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19786","snapshot_observed_at":"2026-07-31T00:46:11.372570Z","title":"Gemma 3 technical report.arXiv preprint arXiv:2503.19786, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.372570Z"},"links":{"cited_paper":"/paper/2503.19786","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:7c85ee9059a5a6e4360000f65ddc9f57bb2a0af1b37bdc1d1136a1e4aeedbfe2","observation_id":"7a474921-a6c5-43b1-b254-736fc062de27","resolution":{"observed_at":"2026-07-31T00:46:11.372570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-07-31T00:46:11.416361Z","title":"Llama: Open and efficient foundation language models.arXiv preprint arXiv:2302.13971, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.416361Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:2ff410c00de9a4d783c3b749da5ca5f04688ed5be8a9762c8e3ae6462d3b0b03","observation_id":"198c3575-9dca-4b02-a0d0-8b0670890d39","resolution":{"observed_at":"2026-07-31T00:46:11.416361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.03256","last_updated":"2024-09-29T06:00:09Z","snapshot_observed_at":"2026-08-16T13:21:11.402721Z","submitted_at":"2024-09-05T05:22:27Z","title":"E2CL: Exploration-based Error Correction Learning for Embodied Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.03256","snapshot_observed_at":"2026-07-31T00:46:11.487704Z","title":"E2cl: exploration-based error correction learning for embodied agents.arXiv preprint arXiv:2409.03256, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.487704Z"},"links":{"cited_paper":"/paper/2409.03256","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:cd7e1a222c964a6c9eaeb793fda0f616d23c1013c4783afbbf9829aec2334c54","observation_id":"c7515389-6d79-4d95-953e-103f9406dcfe","resolution":{"observed_at":"2026-07-31T00:46:11.487704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14276","last_updated":"2025-05-29T16:13:21Z","snapshot_observed_at":"2026-08-16T12:56:47.724696Z","submitted_at":"2025-02-20T05:28:44Z","title":"STeCa: Step-level Trajectory Calibration for LLM Agent Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14276","snapshot_observed_at":"2026-07-31T00:46:11.569078Z","title":"Steca: Step-level trajectory calibration for llm agent learning.arXiv preprint arXiv:2502.14276, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.569078Z"},"links":{"cited_paper":"/paper/2502.14276","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:60e8e07c4ba697890aa8306d5eac95a55cca0d746451793778b34d0176ed3bf6","observation_id":"a924f989-8c55-44ad-9583-168f12eb114c","resolution":{"observed_at":"2026-07-31T00:46:11.569078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.03533","last_updated":"2024-02-22T06:21:51Z","snapshot_observed_at":"2026-07-06T14:27:46.217000Z","submitted_at":"2022-12-07T09:25:54Z","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.03533","snapshot_observed_at":"2026-07-31T00:46:11.647292Z","title":"Text embeddings by weakly-supervised contrastive pre-training","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.647292Z"},"links":{"cited_paper":"/paper/2212.03533","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:05dc5408e68c5ec5c60744bfb6a6f7a20c9c06189cb0ddfab338d8cec6c209bb","observation_id":"0fb0980f-8756-484c-be89-a9d1164bb62b","resolution":{"observed_at":"2026-07-31T00:46:11.647292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08935","last_updated":"2024-02-19T14:07:53Z","snapshot_observed_at":"2026-08-14T10:08:59.886019Z","submitted_at":"2023-12-14T13:41:54Z","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08935","snapshot_observed_at":"2026-07-31T00:46:11.723417Z","title":"Math-shepherd: Verify and reinforce llms step-by-step without human annotations.arXiv preprint arXiv:2312.08935, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.723417Z"},"links":{"cited_paper":"/paper/2312.08935","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:98ad5639ae83d3fddd5a01dcac8e033237ec2094aeda96ebed3005d3becade4f","observation_id":"39dd211c-7a67-42de-993a-d201c6d70c14","resolution":{"observed_at":"2026-07-31T00:46:11.723417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.07540","last_updated":"2022-11-14T17:52:27Z","snapshot_observed_at":"2026-08-16T17:14:35.828935Z","submitted_at":"2022-03-14T22:52:34Z","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.07540","snapshot_observed_at":"2026-07-31T00:46:11.826025Z","title":"Scienceworld: Is your agent smarter than a 5th grader?arXiv preprint arXiv:2203.07540, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.826025Z"},"links":{"cited_paper":"/paper/2203.07540","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:382da90360032252b2ebdca5311771c06ff0ba4c26d0c53766f7b1ac3a0a2a1d","observation_id":"b6e12af4-9680-4d60-9c3d-8c99e48b915d","resolution":{"observed_at":"2026-07-31T00:46:11.826025Z","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":"2026-07-31T00:46:12.029502Z","title":"MiniLMv2: Multi-head self-attention relation distillation for compressing pretrained transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.029502Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:6413a26b6229b7f08067759f95beb3b6970355493121a1084daba6c81eb900a4","observation_id":"efeb57d2-825c-4f96-9eb5-3fc3347418b3","resolution":{"observed_at":"2026-07-31T00:46:12.029502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03268","last_updated":"2024-06-20T18:46:06Z","snapshot_observed_at":"2026-08-16T14:21:18.918564Z","submitted_at":"2024-02-05T18:25:51Z","title":"Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03268","snapshot_observed_at":"2026-07-31T00:46:12.192735Z","title":"Understanding reasoning ability of language models from the perspective of reasoning paths aggregation.arXiv preprint arXiv:2402.03268, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.192735Z"},"links":{"cited_paper":"/paper/2402.03268","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:24f9f43b4149982707836bca77a0ae33fb8c42875f37d9fd2d3e7d138e9d648f","observation_id":"eb4f0de5-af4f-47ae-b31d-6820e173981a","resolution":{"observed_at":"2026-07-31T00:46:12.192735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-08-16T01:49:22.176843Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-07-31T00:46:12.316350Z","title":"Self-consistency improves chain of thought reasoning in language models.arXiv preprint arXiv:2203.11171, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.316350Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:7c71df5e47af0ac9063326c67528243e2466ecacfd384047f3f1dc8f6d0a591c","observation_id":"5476e0eb-a76f-4988-98e1-6bd30cc04fbc","resolution":{"observed_at":"2026-07-31T00:46:12.316350Z","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":"2026-07-31T00:46:12.378019Z","title":"Chain-of-thought prompting elicits reasoning in large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.378019Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:04da095e2605398224da62a4434f34ff376d39f00a26df928bbef9ed8d0d4e30","observation_id":"a4bb834f-72b7-4f23-8a04-6aedd4c845bc","resolution":{"observed_at":"2026-07-31T00:46:12.378019Z","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":"2026-07-31T00:46:12.447926Z","title":"Autogen: Enabling next-gen llm applications via multi-agent conversations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.447926Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:74b31bcff144c8a4d8ebdcf5e035f3265280280c86344bb8278d766d2cc0a7c3","observation_id":"e26d29ad-2c09-49c0-a456-938a9ebea219","resolution":{"observed_at":"2026-07-31T00:46:12.447926Z","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":"2026-07-31T00:46:12.512365Z","title":"Can graph learning improve planning in llm-based agents?Advances in Neural Information Processing Systems, 37:5338–5383, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.512365Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:15ccf2088ec2c98853810d9e01a429af9b0863bb70aadd03962c3fc1968f27a2","observation_id":"f2c914c4-e37f-446b-946b-6629870f81f7","resolution":{"observed_at":"2026-07-31T00:46:12.512365Z","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":"2026-07-31T00:46:12.624226Z","title":"The rise and potential of large language model based agents: A survey.Science China Information Sciences, 68(2):121101, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.624226Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:485f4316940b2d21b17fc76ccca86de59550ad8738d8d197bb9ebbe4a13834cf","observation_id":"16f27dd2-8127-4bc5-a133-56baf189bbc7","resolution":{"observed_at":"2026-07-31T00:46:12.624226Z","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":"2026-07-31T00:46:12.740404Z","title":"Language models meet world models: Embodied experiences enhance language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.740404Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:2f8bffc7c149b34afc0d466ec1fd029523434cb33268a808d82b6a74bb8d9412","observation_id":"4411d582-b2d6-4b25-ad03-bcf70f136094","resolution":{"observed_at":"2026-07-31T00:46:12.740404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14403","last_updated":"2024-02-26T18:29:45Z","snapshot_observed_at":"2026-08-16T14:49:58.802191Z","submitted_at":"2023-10-22T20:28:33Z","title":"O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14403","snapshot_observed_at":"2026-07-31T00:46:12.832422Z","title":"O3d: Offline data-driven discovery and distillation for sequential decision- making with large language models.arXiv preprint arXiv:2310.14403, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.832422Z"},"links":{"cited_paper":"/paper/2310.14403","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:7a30004100a255f3f6f2a8bc3740804b3b4e6308be7d1b07b4b56d33e61cc80a","observation_id":"f7a00d24-7517-4223-8cce-5aedcfa5932d","resolution":{"observed_at":"2026-07-31T00:46:12.832422Z","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":"2026-07-31T00:46:12.895231Z","title":"Travelplanner: A benchmark for real-world planning with language agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.895231Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:cf441491df4c469bbdef45dfd2606e1ec1fcece285ed6d820326367da479fac9","observation_id":"aba49d3b-5652-4c67-961c-2f69238a5e98","resolution":{"observed_at":"2026-07-31T00:46:12.895231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12409","last_updated":"2024-10-16T09:44:38Z","snapshot_observed_at":"2026-08-16T13:08:52.096449Z","submitted_at":"2024-10-16T09:44:38Z","title":"Revealing the Barriers of Language Agents in Planning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12409","snapshot_observed_at":"2026-07-31T00:46:12.898284Z","title":"Revealing the barriers of language agents in planning.arXiv preprint arXiv:2410.12409, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.898284Z"},"links":{"cited_paper":"/paper/2410.12409","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:e81cfe9f5f4f382db671f0e664eece2c2391a2b18aa87a27f1061e886e9562f1","observation_id":"fdc5e345-4185-4a82-943b-3684e0f894a1","resolution":{"observed_at":"2026-07-31T00:46:12.898284Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11176","last_updated":"2024-09-24T10:01:31Z","snapshot_observed_at":"2026-08-16T13:42:26.491534Z","submitted_at":"2024-06-17T03:29:13Z","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11176","snapshot_observed_at":"2026-07-31T00:46:12.901360Z","title":"Watch every step! llm agent learning via iterative step-level process refinement.arXiv preprint arXiv:2406.11176, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.901360Z"},"links":{"cited_paper":"/paper/2406.11176","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:9af3e965bcf9ea060b123cc4d05394936331a431960d6b6442692e423fa8b767","observation_id":"4c53a9ff-d3fa-4631-bbf8-a4207098375a","resolution":{"observed_at":"2026-07-31T00:46:12.901360Z","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":"2026-07-31T00:46:12.904721Z","title":"How powerful are graph neural networks? InInternational Conference on Learning Representations, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.904721Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:19b394199140918a9a30d6e43b513862c99c641947a97cb8334d3d4a6c2db446","observation_id":"3665d2e0-ee52-44f9-a094-88476ef235f7","resolution":{"observed_at":"2026-07-31T00:46:12.904721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-07-31T00:46:12.907736Z","title":"Qwen2.5 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.907736Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:5fc231133ee826e077d01b797072cff4b289156550bae09d243604012251a358","observation_id":"b7bd7473-8618-455d-9ef1-2302b409d8e5","resolution":{"observed_at":"2026-07-31T00:46:12.907736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09560","last_updated":"2025-06-05T07:22:50Z","snapshot_observed_at":"2026-08-15T10:11:58.661690Z","submitted_at":"2025-02-13T18:11:34Z","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09560","snapshot_observed_at":"2026-07-31T00:46:12.910645Z","title":"Embodiedbench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents.arXiv preprint arXiv:2502.09560, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.910645Z"},"links":{"cited_paper":"/paper/2502.09560","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:7fed470e542b0c17dda9cf04ebe871b886ae2e42e0bab05eeeda1989e62ac069","observation_id":"44386acd-0f27-472c-9eb1-2b18717fd673","resolution":{"observed_at":"2026-07-31T00:46:12.910645Z","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":"2026-07-31T00:46:12.913948Z","title":"Gpt4tools: Teaching large language model to use tools via self-instruction.Advances in Neural Information Processing Systems, 36:71995–72007, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.913948Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:b706f221bc6b309e39f755c944bda83bf8ae61e2024e7bd0fdf8307dff24160d","observation_id":"b68f2dd6-f727-4093-9231-c1b15ba9a845","resolution":{"observed_at":"2026-07-31T00:46:12.913948Z","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":"2026-07-31T00:46:12.916727Z","title":"Graph convolutional networks for text classi- fication","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.916727Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:782990d0fd8a2e40cf1428a249134384b352200d39704b10718d58ca64a17375","observation_id":"67f7ee32-913d-4916-9481-fa7b53b66a81","resolution":{"observed_at":"2026-07-31T00:46:12.916727Z","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":"2026-07-31T00:46:12.919502Z","title":"Tree of thoughts: Deliberate problem solving with large language models.Ad- vances in neural information processing systems, 36:11809–11822, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.919502Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:6884f5e7b53d4e827ab7c519d3b839a7b1be27778e693b10d0de69e54ae93681","observation_id":"5aa16c1b-2cb5-4efd-81a5-637840668988","resolution":{"observed_at":"2026-07-31T00:46:12.919502Z","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":"2026-07-31T00:46:12.922269Z","title":"React: Synergizing reasoning and acting in language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.922269Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:fd32a2c02b2f39566a72312c28acd365fdf7866106aab3ba48c22a77b459437c","observation_id":"0698fb16-338c-4d44-bfd3-fd185c82e899","resolution":{"observed_at":"2026-07-31T00:46:12.922269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.08678","last_updated":"2022-03-21T17:49:05Z","snapshot_observed_at":"2026-08-16T17:55:49.524635Z","submitted_at":"2021-09-17T17:58:28Z","title":"RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.08678","snapshot_observed_at":"2026-07-31T00:46:12.925134Z","title":"Rng-kbqa: Generation augmented iterative ranking for knowledge base question answering.arXiv preprint arXiv:2109.08678, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.925134Z"},"links":{"cited_paper":"/paper/2109.08678","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:0d57f094a43f85c7a6f9987039088ea09c90de37d2502d5e91280b1f76444815","observation_id":"352804f7-c15d-48d0-9169-55fbacc523ba","resolution":{"observed_at":"2026-07-31T00:46:12.925134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05657","last_updated":"2024-07-10T17:36:02Z","snapshot_observed_at":"2026-08-16T14:44:48.110154Z","submitted_at":"2023-11-09T00:30:13Z","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05657","snapshot_observed_at":"2026-07-31T00:46:12.928143Z","title":"Agent lumos: Unified and modular training for open-source language agents.arXiv preprint arXiv:2311.05657, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.928143Z"},"links":{"cited_paper":"/paper/2311.05657","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:46767bf10edfa780dd1ccb73d2e6cda846ad07ba7c9d3a544b30de2fe34dca07","observation_id":"73c0d025-43c6-4422-922e-00dc725c5d05","resolution":{"observed_at":"2026-07-31T00:46:12.928143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.11286","last_updated":"2025-08-15T07:48:51Z","snapshot_observed_at":"2026-08-17T03:23:54.723397Z","submitted_at":"2025-08-15T07:48:51Z","title":"Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.11286","snapshot_observed_at":"2026-07-31T00:46:12.931605Z","title":"Scene graph-guided proactive replanning for failure-resilient embodied agent.arXiv preprint arXiv:2508.11286, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.931605Z"},"links":{"cited_paper":"/paper/2508.11286","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:3a13e73b2dad1ccffa161bb967fd8dbb2a226cefa3db7a9bd48063a61760f7b6","observation_id":"d8a465d3-6dde-49d6-9a93-e376c85b6101","resolution":{"observed_at":"2026-07-31T00:46:12.931605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.11425","last_updated":"2025-03-24T10:18:56Z","snapshot_observed_at":"2026-08-15T17:10:35.014170Z","submitted_at":"2025-01-20T11:46:04Z","title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.11425","snapshot_observed_at":"2026-07-31T00:46:12.934662Z","title":"Agent-r: Train- ing language model agents to reflect via iterative self-training.arXiv preprint arXiv:2501.11425, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.934662Z"},"links":{"cited_paper":"/paper/2501.11425","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:63ba42400e43fa786aea28956569ba0454cf742c196150d2ca5b2a182d201cc2","observation_id":"b173eeee-323c-4da1-baa0-0e874dc85a6f","resolution":{"observed_at":"2026-07-31T00:46:12.934662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.07339","last_updated":"2024-08-09T06:16:55Z","snapshot_observed_at":"2026-08-16T14:27:37.602524Z","submitted_at":"2024-01-14T18:12:03Z","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.07339","snapshot_observed_at":"2026-07-31T00:46:12.937645Z","title":"Codeagent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges.arXiv preprint arXiv:2401.07339, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.937645Z"},"links":{"cited_paper":"/paper/2401.07339","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:cc0b215fcdaa48481a2b7f376d714bb3efc5a78ed69f2c98eadf941ee4a931b4","observation_id":"2f25769c-89fe-4995-bbe0-8e188c083be8","resolution":{"observed_at":"2026-07-31T00:46:12.937645Z","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":"2026-07-31T00:46:12.940733Z","title":"Arl: An adaptive reinforcement learning framework for complex question answering over knowledge base.Information Processing & Management, 59(3):102933, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.940733Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:dd63da6c578ae22a6b7ac9b5d18bf90b9faf04b78f20a5253d01d80421793097","observation_id":"3402a092-f409-4ccb-90c5-789e4db94f4c","resolution":{"observed_at":"2026-07-31T00:46:12.940733Z","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":"2026-07-31T00:46:12.943536Z","title":"Active example selection for in-context learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.943536Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:89f5e1ecfc3833cc3beaf1b160dcff66f36a9fd60a7a43292103756f1d01c42c","observation_id":"54cd529a-521b-4073-9421-0a04358e3fab","resolution":{"observed_at":"2026-07-31T00:46:12.943536Z","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":"2026-07-31T00:46:12.946354Z","title":"Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in neural information processing systems, 36:46595–46623, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.946354Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:e51435ae25cb22574c4e3a59448758fd3a863cab2566f4a6e765cfbcb5f666cb","observation_id":"5dd759d3-d44b-4b8e-b14d-e0015be4f827","resolution":{"observed_at":"2026-07-31T00:46:12.946354Z","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":"2026-07-31T00:46:12.949178Z","title":"Trad: Enhancing llm agents with step-wise thought retrieval and aligned decision","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.949178Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:f510bac3482fda29a3708da445f2f161295ea27664634fbec2e700b07d2c97bf","observation_id":"21b41681-068e-4d2d-928e-adc7b5f67220","resolution":{"observed_at":"2026-07-31T00:46:12.949178Z","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":"2026-07-31T00:46:12.952062Z","title":"Large language models are human-level prompt engineers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.952062Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:b98d5bde7d195eb90874f05c48fa0c72a7a1fed6db8910e3c69cec34f5386265","observation_id":"36fee646-d7d0-4ca5-9d4d-677314c6f595","resolution":{"observed_at":"2026-07-31T00:46:12.952062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13227","last_updated":"2023-10-20T02:24:35Z","snapshot_observed_at":"2026-08-16T14:50:31.576522Z","submitted_at":"2023-10-20T02:24:35Z","title":"ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13227","snapshot_observed_at":"2026-07-31T00:46:12.955164Z","title":"clean a plate and put it on the countertop","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.955164Z"},"links":{"cited_paper":"/paper/2310.13227","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:075758aa6a869c32c888144b6cc2ab17f4f1009a36f80a46c4f647a22e1dd3e5","observation_id":"0c8e7268-3137-4be7-8ec5-13fe1a5972c3","resolution":{"observed_at":"2026-07-31T00:46:12.955164Z","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":"2026-07-31T00:46:12.959098Z","title":"{task_goal}","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.959098Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:e3fdefe3a9f75ec9a009d6b417e5b8802a0f0c7fdcb97c552695db828180fe34","observation_id":"49799a31-fb02-4422-911c-6ce13d525e06","resolution":{"observed_at":"2026-07-31T00:46:12.959098Z","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":"2026-07-31T00:46:12.961996Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.961996Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:edbd00feb606c7e4e69a7ef002055e631941f1f18b6c94a88cd4acfdd563a984","observation_id":"645e7dde-709b-442d-ad81-33602554a9a6","resolution":{"observed_at":"2026-07-31T00:46:12.961996Z","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":"2026-07-31T00:46:12.964934Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.964934Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:b99b593e6d7373dfe79102642976830c78688adbdf369385d0a2f0e9af4f6a50","observation_id":"a832d0db-0051-48dc-81a8-ec5d9ec0343f","resolution":{"observed_at":"2026-07-31T00:46:12.964934Z","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":"2026-07-31T00:46:12.967849Z","title":"{current_action}","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.967849Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:4ee606e05d51a33aada53a4f734177398bf66759e5f596e2eedeb16587cb9a78","observation_id":"f2072efe-a08e-47ab-b7ac-dc2a79fefa6d","resolution":{"observed_at":"2026-07-31T00:46:12.967849Z","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":"2026-07-31T00:46:12.970934Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.970934Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:1b2a10418bd9fc5c830528499e4bef2113fda62225273c3676ebd40d3e367989","observation_id":"dd48e540-de4b-49fa-9d99-e4f7621631a9","resolution":{"observed_at":"2026-07-31T00:46:12.970934Z","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":"2026-07-31T00:46:12.973897Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.973897Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:83acbffa5fc62a00bea80ddc3ea0c8756d4ba758279a44572fae8deabf091db8","observation_id":"7328a3f9-ab69-4685-a4ad-7c48bd34aefa","resolution":{"observed_at":"2026-07-31T00:46:12.973897Z","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":"2026-07-31T00:46:12.976617Z","title":"It is not necessary","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.976617Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:d87fab387c7306a4e3c32c35345f03ba172ebecc90cfa166775a816add6cc563","observation_id":"ae76fdb0-68f0-4ac6-bf20-4c6f700c50bf","resolution":{"observed_at":"2026-07-31T00:46:12.976617Z","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":"2026-07-31T00:46:12.979560Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.979560Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:1164d23128f15baffb805e7a89cdf79cd14fc3fb4d97713289d3d40b9799f71c","observation_id":"74f7c599-3a1d-4643-8ed6-a23d8c43a6eb","resolution":{"observed_at":"2026-07-31T00:46:12.979560Z","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":"2026-07-31T00:46:12.982305Z","title":"For example, the current information does not contain the hotel information, so it is not a good time to make final plan","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.982305Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:1e841c3ae8c96ab1584770db1f80e3ddb3564904fbdb9f3a57a448df54a46741","observation_id":"cee01c91-378b-4dfb-829f-d174ca0b34a6","resolution":{"observed_at":"2026-07-31T00:46:12.982305Z","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":"2026-07-31T00:46:12.985114Z","title":"No error","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:12.985114Z"},"links":{"citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:463f08d1f5500ef3dfa0309d0dcfc734311e7b261d0dfdaf6b92b259e717d619","observation_id":"9842080c-2e11-4727-a871-613609e3c0ca","resolution":{"observed_at":"2026-07-31T00:46:12.985114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-14T08:46:40.314502Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems"},"reference_resolution":{"displayed":92,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":91,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":92},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 92 of 92 outbound references and 0 inbound Pith citation observations for arXiv:2607.27443."}