{"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/from-debate-to-equilibrium-belief-driven","title":"From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium","arxiv_id":"2506.08292","date":"2025-06-09","proceeding":null,"authors":["Xie Yi","Zhanke Zhou","Chentao Cao","Qiyu Niu","Tongliang Liu","Bo Han"],"abstract":"Multi-agent frameworks can substantially boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarantees. To overcome these challenges, we recast multi-LLM coordination as an incomplete-information game and seek a Bayesian Nash equilibrium (BNE), in which each agent optimally responds to its probabilistic beliefs about the strategies of others. We introduce Efficient Coordination via Nash Equilibrium (ECON), a hierarchical reinforcement-learning paradigm that marries distributed reasoning with centralized final output. Under ECON, each LLM independently selects responses that maximize its expected reward, conditioned on its beliefs about co-agents, without requiring costly inter-agent exchanges. We mathematically prove that ECON attains a markedly tighter regret bound than non-equilibrium multi-agent schemes. Empirically, ECON outperforms existing multi-LLM approaches by 11.2% on average across six benchmarks spanning complex reasoning and planning tasks. Further experiments demonstrate ECON's ability to flexibly incorporate additional models, confirming its scalability and paving the way toward larger, more powerful multi-LLM ensembles. The code is publicly available at: https://github.com/tmlr-group/ECON.","url_abs":"https://arxiv.org/abs/2506.08292v1","url_pdf":"https://arxiv.org/pdf/2506.08292v1.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":"abstracts"},"code_links":[{"paper_slug":"from-debate-to-equilibrium-belief-driven","repo_url":"https://github.com/tmlr-group/econ","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hierarchical-reinforcement-learning","task_name":"Hierarchical Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2506.08292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08292"}},"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":"deterministic:regex_extraction","url":"https://github.com/tmlr-group/ECON","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tmlr-group/econ","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_fixture":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"b848a56c81c5733e","entry":"BeliefPolicyNetwork","repo":"tmlr-group/econ","repo_kind":"official","path":"src/modules/agents/belief_policy_network.py","file_url":"https://github.com/tmlr-group/econ/blob/HEAD/src/modules/agents/belief_policy_network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b848a56c81c5733e"}},{"code_sha256_prefix":"92c5b4b1b28a5565","entry":"PositionalEncoding","repo":"tmlr-group/econ","repo_kind":"official","path":"src/modules/agents/belief_policy_network.py","file_url":"https://github.com/tmlr-group/econ/blob/HEAD/src/modules/agents/belief_policy_network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92c5b4b1b28a5565"}},{"code_sha256_prefix":"c9580d1c98d9c426","entry":"TransformerBlock","repo":"tmlr-group/econ","repo_kind":"official","path":"src/modules/agents/belief_policy_network.py","file_url":"https://github.com/tmlr-group/econ/blob/HEAD/src/modules/agents/belief_policy_network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9580d1c98d9c426"}},{"code_sha256_prefix":"c294d76e40c17c98","entry":"run_testing","repo":"tmlr-group/econ","repo_kind":"official","path":"scripts/run_p0_test.py","file_url":"https://github.com/tmlr-group/econ/blob/HEAD/scripts/run_p0_test.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c294d76e40c17c98"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}