{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SWQYJUFYJRSTIV6PPJ3UPXA5UA","short_pith_number":"pith:SWQYJUFY","schema_version":"1.0","canonical_sha256":"95a184d0b84c653457cf7a7747dc1da01a23812370a9b623ea2b5e7e1e0b2227","source":{"kind":"arxiv","id":"2412.18371","version":2},"attestation_state":"computed","paper":{"title":"Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jiachi Chen, Jingwen Zhang, Kaiwen Ning, Wei Li, Weizhe Zhang, Yuming Feng, Zexu Wang, Zibin Zheng","submitted_at":"2024-12-24T11:54:14Z","abstract_excerpt":"AI agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in LLM have introduced a transformative paradigm for AI agents, enabling them to interact with external resources and tools through prompts. In such agents, the workflow integrates developer-written code, which manages framework construction and logic control, with LLM-generated natural language that enhances dynamic decision-making and interaction. However, discrepancies between developer-implemented logic and the dynamically generated content of LLMs in terms of behav"},"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":"2412.18371","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-24T11:54:14Z","cross_cats_sorted":[],"title_canon_sha256":"46a7d7b8982f17f34d23feb28abeba24a438792870ce6d212d03c60c21c92147","abstract_canon_sha256":"1a96c9c31d4d35369cb8945a9b6587790127bec01dc2984cdb8169dc3f2106a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:07.905371Z","signature_b64":"MCZDqBrFOwIr6sH+4p7C5bFsbg6NlaasoX11YS5dIjZln+5ExvkoJSRJCEKtDeOz7x/rOERpv6u9QmG21PaZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a184d0b84c653457cf7a7747dc1da01a23812370a9b623ea2b5e7e1e0b2227","last_reissued_at":"2026-07-05T09:54:07.904936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:07.904936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jiachi Chen, Jingwen Zhang, Kaiwen Ning, Wei Li, Weizhe Zhang, Yuming Feng, Zexu Wang, Zibin Zheng","submitted_at":"2024-12-24T11:54:14Z","abstract_excerpt":"AI agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in LLM have introduced a transformative paradigm for AI agents, enabling them to interact with external resources and tools through prompts. In such agents, the workflow integrates developer-written code, which manages framework construction and logic control, with LLM-generated natural language that enhances dynamic decision-making and interaction. However, discrepancies between developer-implemented logic and the dynamically generated content of LLMs in terms of behav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18371","kind":"arxiv","version":2},"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/2412.18371/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":"2412.18371","created_at":"2026-07-05T09:54:07.904994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18371v2","created_at":"2026-07-05T09:54:07.904994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18371","created_at":"2026-07-05T09:54:07.904994+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWQYJUFYJRST","created_at":"2026-07-05T09:54:07.904994+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWQYJUFYJRSTIV6P","created_at":"2026-07-05T09:54:07.904994+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWQYJUFY","created_at":"2026-07-05T09:54:07.904994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22976","citing_title":"LLM Code Smells: A Taxonomy and Detection Approach","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA","json":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA.json","graph_json":"https://pith.science/api/pith-number/SWQYJUFYJRSTIV6PPJ3UPXA5UA/graph.json","events_json":"https://pith.science/api/pith-number/SWQYJUFYJRSTIV6PPJ3UPXA5UA/events.json","paper":"https://pith.science/paper/SWQYJUFY"},"agent_actions":{"view_html":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA","download_json":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA.json","view_paper":"https://pith.science/paper/SWQYJUFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18371&json=true","fetch_graph":"https://pith.science/api/pith-number/SWQYJUFYJRSTIV6PPJ3UPXA5UA/graph.json","fetch_events":"https://pith.science/api/pith-number/SWQYJUFYJRSTIV6PPJ3UPXA5UA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA/action/storage_attestation","attest_author":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA/action/author_attestation","sign_citation":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA/action/citation_signature","submit_replication":"https://pith.science/pith/SWQYJUFYJRSTIV6PPJ3UPXA5UA/action/replication_record"}},"created_at":"2026-07-05T09:54:07.904994+00:00","updated_at":"2026-07-05T09:54:07.904994+00:00"}