{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/reso-a-reward-driven-self-organizing-llm","title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","arxiv_id":"2503.02390","date":"2025-03-04","proceeding":null,"authors":["Heng Zhou","Hejia Geng","Xiangyuan Xue","Li Kang","Yiran Qin","Zhiyong Wang","Zhenfei Yin","Lei Bai"],"abstract":"Multi-agent systems (MAS) have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving; however, current MAS frameworks suffer from poor flexibility and scalability with underdeveloped optimization strategies. To address these challenges, we propose ReSo, which integrates task graph generation with a reward-driven two-stage agent selection process centered on our Collaborative Reward Model that provides fine-grained reward signals to optimize MAS cooperation. We also introduce an automated data synthesis framework for generating MAS benchmarks without any human annotations. Experimental results show that ReSo matches or outperforms existing methods, achieving 33.7 percent accuracy on Math-MAS and 32.3 percent accuracy on SciBench-MAS, where other approaches completely fail.","url_abs":"https://arxiv.org/abs/2503.02390v3","url_pdf":"https://arxiv.org/pdf/2503.02390v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"reso-a-reward-driven-self-organizing-llm","repo_url":"https://github.com/hengzzzhou/reso","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.02390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.02390"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hengzzzhou/reso","reach":null}],"summary":{"ran_violates":2,"ran_draft_wrong":4,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"07e648dea34560c3","entry":"cosine_similarity","repo":"hengzzzhou/reso","repo_kind":"official","path":"ReSo/agent_graph/agent_graph.py","file_url":"https://github.com/hengzzzhou/reso/blob/HEAD/ReSo/agent_graph/agent_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"07e648dea34560c3"}},{"code_sha256_prefix":"1fbb646041496238","entry":"equiv","repo":"hengzzzhou/reso","repo_kind":"official","path":"ReSo/agent_graph/agent_graph.py","file_url":"https://github.com/hengzzzhou/reso/blob/HEAD/ReSo/agent_graph/agent_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1fbb646041496238"}},{"code_sha256_prefix":"b0555fc19e892123","entry":"get_embedding_async","repo":"hengzzzhou/reso","repo_kind":"official","path":"ReSo/agent_graph/agent_graph.py","file_url":"https://github.com/hengzzzhou/reso/blob/HEAD/ReSo/agent_graph/agent_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b0555fc19e892123"}},{"code_sha256_prefix":"94659aac341e7312","entry":"last_boxed_only_string","repo":"hengzzzhou/reso","repo_kind":"official","path":"ReSo/agent_graph/agent_graph.py","file_url":"https://github.com/hengzzzhou/reso/blob/HEAD/ReSo/agent_graph/agent_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94659aac341e7312"}},{"code_sha256_prefix":"636810fa2349bf16","entry":"parse_math_answer","repo":"hengzzzhou/reso","repo_kind":"official","path":"ReSo/agent_graph/agent_graph.py","file_url":"https://github.com/hengzzzhou/reso/blob/HEAD/ReSo/agent_graph/agent_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"636810fa2349bf16"}},{"code_sha256_prefix":"8f1b63da3ae1c5a7","entry":"remove_boxed","repo":"hengzzzhou/reso","repo_kind":"official","path":"ReSo/agent_graph/agent_graph.py","file_url":"https://github.com/hengzzzhou/reso/blob/HEAD/ReSo/agent_graph/agent_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f1b63da3ae1c5a7"}},{"code_sha256_prefix":"c8319903189dc156","entry":"reward_model","repo":"hengzzzhou/reso","repo_kind":"official","path":"ReSo/agent_graph/agent_graph.py","file_url":"https://github.com/hengzzzhou/reso/blob/HEAD/ReSo/agent_graph/agent_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c8319903189dc156"}},{"code_sha256_prefix":"685d8e1ae6d333b9","entry":"AgentGraph","repo":"hengzzzhou/reso","repo_kind":"official","path":"ReSo/agent_graph/agent_graph.py","file_url":"https://github.com/hengzzzhou/reso/blob/HEAD/ReSo/agent_graph/agent_graph.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"685d8e1ae6d333b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}