{"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/enhance-reasoning-for-large-language-models","title":"Enhance Reasoning for Large Language Models in the Game Werewolf","arxiv_id":"2402.02330","date":"2024-02-04","proceeding":null,"authors":["Shuang Wu","Liwen Zhu","Tao Yang","Shiwei Xu","Qiang Fu","Yang Wei","Haobo Fu"],"abstract":"This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents. Unlike augmenting LLMs with prompt engineering, Thinker directly harnesses knowledge from databases and employs various optimization techniques. The framework forms a reasoning hierarchy where LLMs handle intuitive System-1 tasks such as natural language processing, while the Thinker focuses on cognitive System-2 tasks that require complex logical analysis and domain-specific knowledge. Our framework is presented using a 9-player Werewolf game that demands dual-system reasoning. We introduce a communication protocol between LLMs and the Thinker, and train the Thinker using data from 18800 human sessions and reinforcement learning. Experiments demonstrate the framework's effectiveness in deductive reasoning, speech generation, and online game evaluation. Additionally, we fine-tune a 6B LLM to surpass GPT4 when integrated with the Thinker. This paper also contributes the largest dataset for social deduction games to date.","url_abs":"https://arxiv.org/abs/2402.02330v2","url_pdf":"https://arxiv.org/pdf/2402.02330v2.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":"enhance-reasoning-for-large-language-models","repo_url":"https://github.com/boluoweifenda/werewolf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.02330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02330"}},"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/boluoweifenda/werewolf","reach":null}],"summary":{"ran_violates":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"a7636863acf66050","entry":"check_audio","repo":"boluoweifenda/werewolf","repo_kind":"official","path":"processor/check_data_en.py","file_url":"https://github.com/boluoweifenda/werewolf/blob/HEAD/processor/check_data_en.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7636863acf66050"}},{"code_sha256_prefix":"e1fbd7805b53b2d7","entry":"check_game_state","repo":"boluoweifenda/werewolf","repo_kind":"official","path":"processor/check_data_en.py","file_url":"https://github.com/boluoweifenda/werewolf/blob/HEAD/processor/check_data_en.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1fbd7805b53b2d7"}},{"code_sha256_prefix":"8233dbc8233c28b8","entry":"check_label","repo":"boluoweifenda/werewolf","repo_kind":"official","path":"processor/check_data_en.py","file_url":"https://github.com/boluoweifenda/werewolf/blob/HEAD/processor/check_data_en.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8233dbc8233c28b8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}