{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RNLRG7GSXQ6X2HOS37GVV3DSD6","short_pith_number":"pith:RNLRG7GS","schema_version":"1.0","canonical_sha256":"8b57137cd2bc3d7d1dd2dfcd5aec721f80b25193cc1bfc28571c7b04041e9c94","source":{"kind":"arxiv","id":"2607.27443","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chaohao Lin, Dongsheng Luo, Haifeng Chen, Hua Wei, Wei Cheng, Xu Zheng, Zhuomin Chen","submitted_at":"2026-07-29T20:14:43Z","abstract_excerpt":"Large Language Model~(LLM)-based agents have demonstrated exceptional performance across a wide range of complex interactive tasks. However, they often struggle with long-horizon interactive tasks common in domains, such as embodied AI. The complexity and vast action spaces in these settings lead to compounding errors, where a single suboptimal action can derail an entire trajectory, causing the agent to exhaust its limited step budget on inefficient or unrecoverable paths. To overcome this without costly fine-tuning, we draw inspiration from software debugging, where execution logs are analyz"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.27443","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T20:14:43Z","cross_cats_sorted":[],"title_canon_sha256":"3aa9e293cbab34c4d73f7387406891f0828e22e31f806015037305543630b21b","abstract_canon_sha256":"b2e2221b118c7d2a0649321fe240152995b583f089e131c075d5b774abe8f321"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b57137cd2bc3d7d1dd2dfcd5aec721f80b25193cc1bfc28571c7b04041e9c94","last_reissued_at":"2026-07-31T00:12:11.207754Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:12:11.207754Z"},"graph_snapshot":{"paper":{"title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chaohao Lin, Dongsheng Luo, Haifeng Chen, Hua Wei, Wei Cheng, Xu Zheng, Zhuomin Chen","submitted_at":"2026-07-29T20:14:43Z","abstract_excerpt":"Large Language Model~(LLM)-based agents have demonstrated exceptional performance across a wide range of complex interactive tasks. However, they often struggle with long-horizon interactive tasks common in domains, such as embodied AI. The complexity and vast action spaces in these settings lead to compounding errors, where a single suboptimal action can derail an entire trajectory, causing the agent to exhaust its limited step budget on inefficient or unrecoverable paths. To overcome this without costly fine-tuning, we draw inspiration from software debugging, where execution logs are analyz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27443","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.27443/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.27443","created_at":"2026-07-31T00:12:11.210059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27443v1","created_at":"2026-07-31T00:12:11.210059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27443","created_at":"2026-07-31T00:12:11.210059+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNLRG7GSXQ6X","created_at":"2026-07-31T00:12:11.210059+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNLRG7GSXQ6X2HOS","created_at":"2026-07-31T00:12:11.210059+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNLRG7GS","created_at":"2026-07-31T00:12:11.210059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6","json":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6.json","graph_json":"https://pith.science/api/pith-number/RNLRG7GSXQ6X2HOS37GVV3DSD6/graph.json","events_json":"https://pith.science/api/pith-number/RNLRG7GSXQ6X2HOS37GVV3DSD6/events.json","paper":"https://pith.science/paper/RNLRG7GS"},"agent_actions":{"view_html":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6","download_json":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6.json","view_paper":"https://pith.science/paper/RNLRG7GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27443&json=true","fetch_graph":"https://pith.science/api/pith-number/RNLRG7GSXQ6X2HOS37GVV3DSD6/graph.json","fetch_events":"https://pith.science/api/pith-number/RNLRG7GSXQ6X2HOS37GVV3DSD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6/action/storage_attestation","attest_author":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6/action/author_attestation","sign_citation":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6/action/citation_signature","submit_replication":"https://pith.science/pith/RNLRG7GSXQ6X2HOS37GVV3DSD6/action/replication_record"}},"created_at":"2026-07-31T00:12:11.210059+00:00","updated_at":"2026-07-31T00:12:11.210059+00:00"}