{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q25YYUX2AN6YCPWQ5ZKTBBF4OG","short_pith_number":"pith:Q25YYUX2","schema_version":"1.0","canonical_sha256":"86bb8c52fa037d813ed0ee553084bc71a90c44ab2ab217a16c7e5a0a1dcdfed1","source":{"kind":"arxiv","id":"2408.00989","version":4},"attestation_state":"computed","paper":{"title":"On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jen-tse Huang, Jiaxu Zhou, Maarten Sap, Michael R. Lyu, Tailin Jin, Wenxuan Wang, Xuhui Zhou, Youliang Yuan, Zixi Chen","submitted_at":"2024-08-02T03:25:20Z","abstract_excerpt":"Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored. This paper investigates: (1) What is the resilience of various system structures (e.g., A$\\rightarrow$B$\\rightarrow$C, A$\\leftrightarrow$B$\\leftrightarrow$C) under faulty agents, on different downstream tasks? (2) How can we increase system resilience to de"},"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":"2408.00989","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-02T03:25:20Z","cross_cats_sorted":[],"title_canon_sha256":"193ebc81db7b55cc4a5557b9c3a2dd66fa411a317a9b836da1455c091b15e16a","abstract_canon_sha256":"144e4841e3c330e66e4976c9869d90f8d0ffbc9231f04a07dadcc045c506f0e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:33.786997Z","signature_b64":"+/RyxeS2gw05FjX0szv68Vig7+dlL+TWznoZhI3boM1RBaNZdA8OizmvmHLvhhwud3qR5gxt0+DDJGXqGDbFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86bb8c52fa037d813ed0ee553084bc71a90c44ab2ab217a16c7e5a0a1dcdfed1","last_reissued_at":"2026-07-05T11:11:33.786447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:33.786447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jen-tse Huang, Jiaxu Zhou, Maarten Sap, Michael R. Lyu, Tailin Jin, Wenxuan Wang, Xuhui Zhou, Youliang Yuan, Zixi Chen","submitted_at":"2024-08-02T03:25:20Z","abstract_excerpt":"Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored. This paper investigates: (1) What is the resilience of various system structures (e.g., A$\\rightarrow$B$\\rightarrow$C, A$\\leftrightarrow$B$\\leftrightarrow$C) under faulty agents, on different downstream tasks? (2) How can we increase system resilience to de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00989","kind":"arxiv","version":4},"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/2408.00989/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":"2408.00989","created_at":"2026-07-05T11:11:33.786528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00989v4","created_at":"2026-07-05T11:11:33.786528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00989","created_at":"2026-07-05T11:11:33.786528+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q25YYUX2AN6Y","created_at":"2026-07-05T11:11:33.786528+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q25YYUX2AN6YCPWQ","created_at":"2026-07-05T11:11:33.786528+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q25YYUX2","created_at":"2026-07-05T11:11:33.786528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21666","citing_title":"Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18795","citing_title":"Opinion Polarization in LLM-Based Social Networks: Manipulation and Mitigation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03467","citing_title":"StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16346","citing_title":"PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02546","citing_title":"To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2508.04691","citing_title":"Before Humans Join the Team: Diagnosing Coordination Failures in Healthcare Robot Team Simulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2510.23883","citing_title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","ref_index":254,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27771","citing_title":"Emergent Social Intelligence Risks in Generative Multi-Agent Systems","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13213","citing_title":"Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12364","citing_title":"Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06320","citing_title":"Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG","json":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG.json","graph_json":"https://pith.science/api/pith-number/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/graph.json","events_json":"https://pith.science/api/pith-number/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/events.json","paper":"https://pith.science/paper/Q25YYUX2"},"agent_actions":{"view_html":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG","download_json":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG.json","view_paper":"https://pith.science/paper/Q25YYUX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00989&json=true","fetch_graph":"https://pith.science/api/pith-number/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/graph.json","fetch_events":"https://pith.science/api/pith-number/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/action/storage_attestation","attest_author":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/action/author_attestation","sign_citation":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/action/citation_signature","submit_replication":"https://pith.science/pith/Q25YYUX2AN6YCPWQ5ZKTBBF4OG/action/replication_record"}},"created_at":"2026-07-05T11:11:33.786528+00:00","updated_at":"2026-07-05T11:11:33.786528+00:00"}