{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W7CFVEO2ERVEZ2GB7KWYLBTNSC","short_pith_number":"pith:W7CFVEO2","schema_version":"1.0","canonical_sha256":"b7c45a91da246a4ce8c1faad85866d90a4a661d6b5493190b0c4767ca2b79085","source":{"kind":"arxiv","id":"2308.10848","version":3},"attestation_state":"computed","paper":{"title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multi-agent groups powered by LLMs outperform single agents by dynamically adjusting their composition and interactions.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenfei Yuan, Cheng Yang, Chen Qian, Chi-Min Chan, Heyang Yu, Jie Zhou, Jingwei Zuo, Maosong Sun, Ruobing Xie, Weize Chen, Xin Cong, Yaxi Lu, Yi-Hsin Hung, Yujia Qin, Yusheng Su, Zhiyuan Liu","submitted_at":"2023-08-21T16:47:11Z","abstract_excerpt":"Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework \\framework that can collaboratively and dynamically adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that \\framework framework can effectively deploy multi-agent "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2308.10848","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T16:47:11Z","cross_cats_sorted":[],"title_canon_sha256":"82781864227db3d7a6ef8b3c6d4ad3a4a3e84dff18dfbf00487d64314fbb4038","abstract_canon_sha256":"70c74d16e2fd5b7a25c01c207936b87016113dcded273ab88a6cf6009f2a7228"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.378191Z","signature_b64":"X/4BSSGXDLWgubIXU36i25HpXV+FdAVfpXMrFDFk5NwNLMlkf45+qTEI9o/lqsC5oU/eTL/yudRo5z1RwvJ6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7c45a91da246a4ce8c1faad85866d90a4a661d6b5493190b0c4767ca2b79085","last_reissued_at":"2026-05-17T23:38:50.377769Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.377769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multi-agent groups powered by LLMs outperform single agents by dynamically adjusting their composition and interactions.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenfei Yuan, Cheng Yang, Chen Qian, Chi-Min Chan, Heyang Yu, Jie Zhou, Jingwei Zuo, Maosong Sun, Ruobing Xie, Weize Chen, Xin Cong, Yaxi Lu, Yi-Hsin Hung, Yujia Qin, Yusheng Su, Zhiyuan Liu","submitted_at":"2023-08-21T16:47:11Z","abstract_excerpt":"Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework \\framework that can collaboratively and dynamically adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that \\framework framework can effectively deploy multi-agent "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our experiments demonstrate that AgentVerse framework can effectively deploy multi-agent groups that outperform a single agent. Furthermore, we delve into the emergence of social behaviors among individual agents within a group during collaborative task accomplishment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that dynamic adjustment of group composition and collaboration mechanisms reliably produce superior performance and controllable emergent behaviors, as specific implementation details, baselines, and controls are not provided in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AgentVerse enables dynamic multi-agent collaboration among LLM agents to outperform single agents while revealing emergent social behaviors during task completion.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-agent groups powered by LLMs outperform single agents by dynamically adjusting their composition and interactions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"35e142116333bb7f665bef60e7a4f010ebde45bb28147ea495a67daeed2006a9"},"source":{"id":"2308.10848","kind":"arxiv","version":3},"verdict":{"id":"b507aaf6-4e43-4881-a8a9-95d0b7e65364","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T19:41:07.915761Z","strongest_claim":"Our experiments demonstrate that AgentVerse framework can effectively deploy multi-agent groups that outperform a single agent. Furthermore, we delve into the emergence of social behaviors among individual agents within a group during collaborative task accomplishment.","one_line_summary":"AgentVerse enables dynamic multi-agent collaboration among LLM agents to outperform single agents while revealing emergent social behaviors during task completion.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that dynamic adjustment of group composition and collaboration mechanisms reliably produce superior performance and controllable emergent behaviors, as specific implementation details, baselines, and controls are not provided in the abstract.","pith_extraction_headline":"Multi-agent groups powered by LLMs outperform single agents by dynamically adjusting their composition and interactions."},"references":{"count":100,"sample":[{"doi":"10.48550/arxiv.2305.14325","year":1998,"title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","work_id":"a543e65c-1cf8-4182-b03b-33c0cd2c65d5","ref_index":1,"cited_arxiv_id":"2305.14325","is_internal_anchor":true},{"doi":"","year":null,"title":"’Heat Waves’ by Glass Animals","work_id":"cb201dce-90c0-4948-b332-b425630f8ad9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"’We Don’t Talk About Bruno’ by Carolina Gaitan, Mauro Castillo, Adassa, Rhenzy Feliz, Diane Guerrero, Stephanie Beatriz & Encanto Cast","work_id":"5725e91b-8e07-4c22-bbc4-01f255816e62","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"’Super Gremlin’ by Kodak Black","work_id":"72cd1ae2-b0a4-49fa-98ab-0201f4444cb5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"’Slime You Out’ by Drake Featuring SZA","work_id":"31ee5ba1-d817-47a0-b875-3abb7e59fcc2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":100,"snapshot_sha256":"802547dd8cb99679b21fff719fd7bcefa0a0ff19217ae5afe439858b8f38e2a2","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"11403da7892682d872dc79f4310d41a7ca3eb188700ff025a9a07bde315a2757"},"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":"2308.10848","created_at":"2026-05-17T23:38:50.377835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10848v3","created_at":"2026-05-17T23:38:50.377835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10848","created_at":"2026-05-17T23:38:50.377835+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7CFVEO2ERVE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7CFVEO2ERVEZ2GB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7CFVEO2","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":33,"sample":[{"citing_arxiv_id":"2510.05746","citing_title":"ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12824","citing_title":"Mechanism Plausibility in Generative Agent-Based Modeling","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18890","citing_title":"Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20173","citing_title":"A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00432","citing_title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","ref_index":118,"is_internal_anchor":true},{"citing_arxiv_id":"2510.05174","citing_title":"Emergent Coordination in Multi-Agent Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2404.11584","citing_title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2601.14053","citing_title":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2603.07880","citing_title":"What Do AI Agents Talk About? Discourse and Architectural Constraints in the First AI-Only Social Network","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09127","citing_title":"Collective AI can amplify tiny perturbations into divergent decisions","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":156,"is_internal_anchor":true},{"citing_arxiv_id":"2312.13010","citing_title":"AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12824","citing_title":"Mechanism Plausibility in Generative Agent-Based Modeling","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2305.19118","citing_title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03888","citing_title":"PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27271","citing_title":"Frame Entrepreneurs in an AI Agent Community: Concentrated Identity-Claim Production on Moltbook","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27271","citing_title":"Frame Entrepreneurs in an AI Agent Community: Concentrated Identity-Claim Production on Moltbook","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10052","citing_title":"Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2402.01680","citing_title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27271","citing_title":"Frame Entrepreneurs in an AI Agent Community: Concentrated Identity-Claim Production on Moltbook","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23579","citing_title":"CineAGI: Character-Consistent Movie Creation through LLM-Orchestrated Multi-Modal Generation and Cross-Scene Integration","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC","json":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC.json","graph_json":"https://pith.science/api/pith-number/W7CFVEO2ERVEZ2GB7KWYLBTNSC/graph.json","events_json":"https://pith.science/api/pith-number/W7CFVEO2ERVEZ2GB7KWYLBTNSC/events.json","paper":"https://pith.science/paper/W7CFVEO2"},"agent_actions":{"view_html":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC","download_json":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC.json","view_paper":"https://pith.science/paper/W7CFVEO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10848&json=true","fetch_graph":"https://pith.science/api/pith-number/W7CFVEO2ERVEZ2GB7KWYLBTNSC/graph.json","fetch_events":"https://pith.science/api/pith-number/W7CFVEO2ERVEZ2GB7KWYLBTNSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC/action/storage_attestation","attest_author":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC/action/author_attestation","sign_citation":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC/action/citation_signature","submit_replication":"https://pith.science/pith/W7CFVEO2ERVEZ2GB7KWYLBTNSC/action/replication_record"}},"created_at":"2026-05-17T23:38:50.377835+00:00","updated_at":"2026-05-17T23:38:50.377835+00:00"}