{"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/interpretable-contrastive-monte-carlo-tree","title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","arxiv_id":"2410.01707","date":"2024-10-02","proceeding":null,"authors":["Zitian Gao","Boye Niu","Xuzheng He","Haotian Xu","Hongzhang Liu","Aiwei Liu","Xuming Hu","Lijie Wen"],"abstract":"We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our motivation comes from: 1. Previous MCTS LLM reasoning works often overlooked its biggest drawback--slower speed compared to CoT; 2. Previous research mainly used MCTS as a tool for LLM reasoning on various tasks with limited quantitative analysis or ablation studies of its components from reasoning interpretability perspective. 3. The reward model is the most crucial component in MCTS, however previous work has rarely conducted in-depth study or improvement of MCTS's reward models. Thus, we conducted extensive ablation studies and quantitative analysis on components of MCTS, revealing the impact of each component on the MCTS reasoning performance of LLMs. Building on this, (i) we designed a highly interpretable reward model based on the principle of contrastive decoding and (ii) achieved an average speed improvement of 51.9% per node using speculative decoding. Additionally, (iii) we improved UCT node selection strategy and backpropagation used in previous works, resulting in significant performance improvement. We outperformed o1-mini by an average of 17.4% on the Blocksworld multi-step reasoning dataset using Llama-3.1-70B with SC-MCTS*. Our code is available at https://github.com/zitian-gao/SC-MCTS.","url_abs":"https://arxiv.org/abs/2410.01707v3","url_pdf":"https://arxiv.org/pdf/2410.01707v3.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":"interpretable-contrastive-monte-carlo-tree","repo_url":"https://github.com/zitian-gao/sc-mcts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.01707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01707"}},"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/zitian-gao/sc-mcts","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"d90672da961a8499","entry":"fill_template","repo":"zitian-gao/sc-mcts","repo_kind":"official","path":"reasoners/bw_utils.py","file_url":"https://github.com/zitian-gao/sc-mcts/blob/HEAD/reasoners/bw_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d90672da961a8499"}},{"code_sha256_prefix":"7f438ad971434c41","entry":"get_icl","repo":"zitian-gao/sc-mcts","repo_kind":"official","path":"reasoners/blocksworld.py","file_url":"https://github.com/zitian-gao/sc-mcts/blob/HEAD/reasoners/blocksworld.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f438ad971434c41"}},{"code_sha256_prefix":"485b2065c7a827ec","entry":"instance_to_text_blocksworld","repo":"zitian-gao/sc-mcts","repo_kind":"official","path":"reasoners/bw_utils.py","file_url":"https://github.com/zitian-gao/sc-mcts/blob/HEAD/reasoners/bw_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"485b2065c7a827ec"}},{"code_sha256_prefix":"685060993657f12c","entry":"parse_problem","repo":"zitian-gao/sc-mcts","repo_kind":"official","path":"reasoners/bw_utils.py","file_url":"https://github.com/zitian-gao/sc-mcts/blob/HEAD/reasoners/bw_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"685060993657f12c"}},{"code_sha256_prefix":"8df40ca54d86c1ad","entry":"rap_bw_extractor","repo":"zitian-gao/sc-mcts","repo_kind":"official","path":"reasoners/blocksworld.py","file_url":"https://github.com/zitian-gao/sc-mcts/blob/HEAD/reasoners/blocksworld.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8df40ca54d86c1ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}