{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VKQR6QF5DZZ3QLOO7IE6G3CYT7","short_pith_number":"pith:VKQR6QF5","schema_version":"1.0","canonical_sha256":"aaa11f40bd1e73b82dcefa09e36c589fe28caeb7ef6141ae42763e6d6da63ab8","source":{"kind":"arxiv","id":"2508.13167","version":1},"attestation_state":"computed","paper":{"title":"Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chenghao Zhu, Dingfeng Shi, Ge Zhang, He Zhu, Hongxuan Lu, Jiaheng Liu, Jianbo Lin, Jian Yang, Jiayu Zhang, Jingyi Cao, King Zhu, Minghao Liu, Pai Liu, Piaohong Wang, Qianben Chen, Qiexiang Wang, Shuying Fan, Tiannan Wang, Tianrui Qin, Wangchunshu Zhou, Weichen Sun, Weizhen Li, Xiangru Tang, Xiaowan Li, Xinpeng Liu, Yeyi Guan, Yi Yao, Yuchen Eleanor Jiang, Zhenqiang Huang, Zhuosong Jiang","submitted_at":"2025-08-06T17:01:02Z","abstract_excerpt":"Recent advances in large language models (LLMs) and multi-agent systems have demonstrated remarkable capabilities in complex problem-solving tasks such as deep research, vibe coding, and mathematical reasoning. However, most existing multi-agent systems are built upon manual prompt/workflow engineering with sophisticated agent frameworks, making them computationally inefficient, less capable, and can not benefit from data-centric learning. In this work, we introduce Chain-of-Agents (CoA), a novel paradigm of LLM reasoning that enables native end-to-end complex problem-solving in the same way a"},"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":"2508.13167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-06T17:01:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c14b64a650d65400903c77c1fedc8fb6716809fd58993d718e1fd33c79366a25","abstract_canon_sha256":"5e5540557389f6304675a4e0f750e5e026f8e2ec722194bf7617d4dd9b58f459"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:43.540606Z","signature_b64":"YGNbS5+pHxcb4zAzyI9cMjygZwq8Z6FOCs7YMkkVRsQgq3LicV2s9xxq7BKCwhaIqJw9IWxbyGv7s7eFgZhvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aaa11f40bd1e73b82dcefa09e36c589fe28caeb7ef6141ae42763e6d6da63ab8","last_reissued_at":"2026-07-05T11:55:43.540075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:43.540075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chenghao Zhu, Dingfeng Shi, Ge Zhang, He Zhu, Hongxuan Lu, Jiaheng Liu, Jianbo Lin, Jian Yang, Jiayu Zhang, Jingyi Cao, King Zhu, Minghao Liu, Pai Liu, Piaohong Wang, Qianben Chen, Qiexiang Wang, Shuying Fan, Tiannan Wang, Tianrui Qin, Wangchunshu Zhou, Weichen Sun, Weizhen Li, Xiangru Tang, Xiaowan Li, Xinpeng Liu, Yeyi Guan, Yi Yao, Yuchen Eleanor Jiang, Zhenqiang Huang, Zhuosong Jiang","submitted_at":"2025-08-06T17:01:02Z","abstract_excerpt":"Recent advances in large language models (LLMs) and multi-agent systems have demonstrated remarkable capabilities in complex problem-solving tasks such as deep research, vibe coding, and mathematical reasoning. However, most existing multi-agent systems are built upon manual prompt/workflow engineering with sophisticated agent frameworks, making them computationally inefficient, less capable, and can not benefit from data-centric learning. In this work, we introduce Chain-of-Agents (CoA), a novel paradigm of LLM reasoning that enables native end-to-end complex problem-solving in the same way a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13167","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/2508.13167/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":"2508.13167","created_at":"2026-07-05T11:55:43.540137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13167v1","created_at":"2026-07-05T11:55:43.540137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13167","created_at":"2026-07-05T11:55:43.540137+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKQR6QF5DZZ3","created_at":"2026-07-05T11:55:43.540137+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKQR6QF5DZZ3QLOO","created_at":"2026-07-05T11:55:43.540137+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKQR6QF5","created_at":"2026-07-05T11:55:43.540137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06935","citing_title":"Mathematical methods of reinforcement learning","ref_index":121,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17931","citing_title":"LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09138","citing_title":"Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":262,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22138","citing_title":"Efficient Agentic Reasoning Through Self-Regulated Simulative Planning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15224","citing_title":"ICRL: Learning to Internalize Self-Critique with Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":283,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11793","citing_title":"MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08124","citing_title":"Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04496","citing_title":"SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01347","citing_title":"MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07725","citing_title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06170","citing_title":"Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18292","citing_title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7","json":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7.json","graph_json":"https://pith.science/api/pith-number/VKQR6QF5DZZ3QLOO7IE6G3CYT7/graph.json","events_json":"https://pith.science/api/pith-number/VKQR6QF5DZZ3QLOO7IE6G3CYT7/events.json","paper":"https://pith.science/paper/VKQR6QF5"},"agent_actions":{"view_html":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7","download_json":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7.json","view_paper":"https://pith.science/paper/VKQR6QF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13167&json=true","fetch_graph":"https://pith.science/api/pith-number/VKQR6QF5DZZ3QLOO7IE6G3CYT7/graph.json","fetch_events":"https://pith.science/api/pith-number/VKQR6QF5DZZ3QLOO7IE6G3CYT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7/action/storage_attestation","attest_author":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7/action/author_attestation","sign_citation":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7/action/citation_signature","submit_replication":"https://pith.science/pith/VKQR6QF5DZZ3QLOO7IE6G3CYT7/action/replication_record"}},"created_at":"2026-07-05T11:55:43.540137+00:00","updated_at":"2026-07-05T11:55:43.540137+00:00"}