{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P6XAGWUNFY36QJ3JQDYMDE4JWS","short_pith_number":"pith:P6XAGWUN","schema_version":"1.0","canonical_sha256":"7fae035a8d2e37e8276980f0c19389b483d7cd78262fdef824373b1f75701359","source":{"kind":"arxiv","id":"2303.17760","version":2},"attestation_state":"computed","paper":{"title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Role-playing with inception prompting lets language models form cooperative agent teams that complete complex tasks with minimal human guidance.","cross_cats":["cs.CL","cs.CY","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Bernard Ghanem, Dmitrii Khizbullin, Guohao Li, Hani Itani, Hasan Abed Al Kader Hammoud","submitted_at":"2023-03-31T01:09:00Z","abstract_excerpt":"The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents, and provides insight into their \"cognitive\" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting t"},"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":"2303.17760","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-31T01:09:00Z","cross_cats_sorted":["cs.CL","cs.CY","cs.LG","cs.MA"],"title_canon_sha256":"ac20e0aa0da9dce499f4db8959fa5c1d6f0d726115999329a6b90de1fda5045d","abstract_canon_sha256":"e2a3cd31ade34ccb54bb37a9887987c80a0f1b148ff8085994116eb93e44c839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:50:49.721213Z","signature_b64":"Ek8v163s70ofBh36r2yIKqGCTFb88tLE7UrV5I/ySzrxwl6HiY+/aUCbFt43/BRyh8dHNsOPXlr0wN1WWU19Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fae035a8d2e37e8276980f0c19389b483d7cd78262fdef824373b1f75701359","last_reissued_at":"2026-05-18T02:50:49.720501Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:50:49.720501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Role-playing with inception prompting lets language models form cooperative agent teams that complete complex tasks with minimal human guidance.","cross_cats":["cs.CL","cs.CY","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Bernard Ghanem, Dmitrii Khizbullin, Guohao Li, Hani Itani, Hasan Abed Al Kader Hammoud","submitted_at":"2023-03-31T01:09:00Z","abstract_excerpt":"The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents, and provides insight into their \"cognitive\" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That large language models will reliably maintain assigned roles and produce coherent, on-task responses across extended multi-turn conversations without external correction or drift.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Role-playing with inception prompting lets language models form cooperative agent teams that complete complex tasks with minimal human guidance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2d09f8f53972b1c17dba03290016fef1e3863e504454d530504f93ff6224151f"},"source":{"id":"2303.17760","kind":"arxiv","version":2},"verdict":{"id":"d38c43db-0f8d-481d-a8ee-548277d02627","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T01:36:38.827502Z","strongest_claim":"Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions.","one_line_summary":"CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That large language models will reliably maintain assigned roles and produce coherent, on-task responses across extended multi-turn conversations without external correction or drift.","pith_extraction_headline":"Role-playing with inception prompting lets language models form cooperative agent teams that complete complex tasks with minimal human guidance."},"references":{"count":137,"sample":[{"doi":"","year":2020,"title":"Imitating interactive intelligence","work_id":"91d7ba28-dd0f-4a93-8713-612c8e619a2d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Do as i can, not as i say: Grounding language in robotic affordances","work_id":"0a87d969-8ace-450a-97bf-6d2116e18162","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Language models as agent models","work_id":"495830ab-e80f-48fb-a342-36b9197eb581","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Alignment-based compositional semantics for instruction following","work_id":"d4d637b8-7a21-45df-b0a5-015d69140127","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Introducing claude","work_id":"d2de5c73-f7e6-47bb-ae16-ad262e3c853b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":137,"snapshot_sha256":"a9d7b3967d36d75bb92291117ee7aa9d5763dfc0d3500fb0a8e5b18906b71069","internal_anchors":27},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ea3db82ce5f278db293e99e15b9bc09f30534dce8c5c36c1f16ed9fb5524bdd8"},"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":"2303.17760","created_at":"2026-05-18T02:50:49.720625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17760v2","created_at":"2026-05-18T02:50:49.720625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17760","created_at":"2026-05-18T02:50:49.720625+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6XAGWUNFY36","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6XAGWUNFY36QJ3J","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6XAGWUN","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":42,"internal_anchor_count":42,"sample":[{"citing_arxiv_id":"2605.17998","citing_title":"Verify-Gated Completion as Admission Control in a Governed Multi-Agent Runtime: A Bounded Architecture Case Study","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2510.07799","citing_title":"Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24697","citing_title":"Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17694","citing_title":"Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17998","citing_title":"Verify-Gated Completion as Admission Control in a Governed Multi-Agent Runtime: A Bounded Architecture Case Study","ref_index":2,"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":22,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":252,"is_internal_anchor":true},{"citing_arxiv_id":"2309.05653","citing_title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2402.03578","citing_title":"LLM Multi-Agent Systems: Challenges and Open Problems","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2511.21783","citing_title":"NetworkGames: Simulating Cooperation in Network Games with Personality-driven LLM Agents","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2512.24329","citing_title":"World model inspired sarcasm reasoning with large language model agents","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2601.00911","citing_title":"Device-Native Autonomous Agents for Privacy-Preserving Negotiations","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2305.14233","citing_title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","ref_index":245,"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":24,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09127","citing_title":"Collective AI can amplify tiny perturbations into divergent decisions","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2308.07201","citing_title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","ref_index":12,"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":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11789","citing_title":"Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulations","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12087","citing_title":"Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2311.12983","citing_title":"GAIA: a benchmark for General AI Assistants","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS","json":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS.json","graph_json":"https://pith.science/api/pith-number/P6XAGWUNFY36QJ3JQDYMDE4JWS/graph.json","events_json":"https://pith.science/api/pith-number/P6XAGWUNFY36QJ3JQDYMDE4JWS/events.json","paper":"https://pith.science/paper/P6XAGWUN"},"agent_actions":{"view_html":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS","download_json":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS.json","view_paper":"https://pith.science/paper/P6XAGWUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17760&json=true","fetch_graph":"https://pith.science/api/pith-number/P6XAGWUNFY36QJ3JQDYMDE4JWS/graph.json","fetch_events":"https://pith.science/api/pith-number/P6XAGWUNFY36QJ3JQDYMDE4JWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS/action/storage_attestation","attest_author":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS/action/author_attestation","sign_citation":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS/action/citation_signature","submit_replication":"https://pith.science/pith/P6XAGWUNFY36QJ3JQDYMDE4JWS/action/replication_record"}},"created_at":"2026-05-18T02:50:49.720625+00:00","updated_at":"2026-05-18T02:50:49.720625+00:00"}