{"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/rest-mcts-llm-self-training-via-process","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","arxiv_id":"2406.03816","date":"2024-06-06","proceeding":null,"authors":["Dan Zhang","Sining Zhoubian","Ziniu Hu","Yisong Yue","Yuxiao Dong","Jie Tang"],"abstract":"Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or intermediate reasoning). In this paper, we develop a reinforced self-training approach, called ReST-MCTS*, based on integrating process reward guidance with tree search MCTS* for collecting higher-quality reasoning traces as well as per-step value to train policy and reward models. ReST-MCTS* circumvents the per-step manual annotation typically used to train process rewards by tree-search-based reinforcement learning: Given oracle final correct answers, ReST-MCTS* is able to infer the correct process rewards by estimating the probability this step can help lead to the correct answer. These inferred rewards serve dual purposes: they act as value targets for further refining the process reward model and also facilitate the selection of high-quality traces for policy model self-training. We first show that the tree-search policy in ReST-MCTS* achieves higher accuracy compared with prior LLM reasoning baselines such as Best-of-N and Tree-of-Thought, within the same search budget. We then show that by using traces searched by this tree-search policy as training data, we can continuously enhance the three language models for multiple iterations, and outperform other self-training algorithms such as ReST$^\\text{EM}$ and Self-Rewarding LM. We release all code at https://github.com/THUDM/ReST-MCTS.","url_abs":"https://arxiv.org/abs/2406.03816v3","url_pdf":"https://arxiv.org/pdf/2406.03816v3.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":"rest-mcts-llm-self-training-via-process","repo_url":"https://github.com/THUDM/ReST-MCTS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rest-mcts-llm-self-training-via-process","repo_url":"https://github.com/DIRECT-BIT/SRA-MCTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.03816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03816"}},"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/THUDM/ReST-MCTS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DIRECT-BIT/SRA-MCTS","reach":null}],"summary":{"ran_draft_wrong":7,"ran_violates":1,"ran":1,"unverified":13},"by_repo_kind":{"official":{"samples":13,"ran":6,"repositories":1},"listed":{"samples":9,"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":13,"samples":[{"code_sha256_prefix":"fb7427c831c79168","entry":"getBestChild","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"fb7427c831c79168"}},{"code_sha256_prefix":"a291959b6558d330","entry":"getBestChild","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a291959b6558d330"}},{"code_sha256_prefix":"91b601baaf0d2b44","entry":"get_next_steps_roll","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91b601baaf0d2b44"}},{"code_sha256_prefix":"d48bb511335b496a","entry":"get_next_steps_roll","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d48bb511335b496a"}},{"code_sha256_prefix":"63ea91a630010b0e","entry":"gpt_usage","repo":"thudm/rest-mcts","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/thudm/rest-mcts/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63ea91a630010b0e"}},{"code_sha256_prefix":"04c9e8ce083656fc","entry":"isTerminal","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"04c9e8ce083656fc"}},{"code_sha256_prefix":"88d52f64be6d8180","entry":"selectNode","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"88d52f64be6d8180"}},{"code_sha256_prefix":"3e9b96d2d986aaae","entry":"selectNode","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e9b96d2d986aaae"}},{"code_sha256_prefix":"ca2e487758bc8d8b","entry":"treeNode","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"ca2e487758bc8d8b"}},{"code_sha256_prefix":"9c7f89c86df49382","entry":"MCTS_search","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"9c7f89c86df49382"}},{"code_sha256_prefix":"e819d89ad4828066","entry":"MCTS_search","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e819d89ad4828066"}},{"code_sha256_prefix":"15d94bcdfc2d9d1b","entry":"back_propagate","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"15d94bcdfc2d9d1b"}},{"code_sha256_prefix":"68319c1da6a20dbd","entry":"executeRound","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"68319c1da6a20dbd"}},{"code_sha256_prefix":"0f8338c98de6cd72","entry":"executeRound","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f8338c98de6cd72"}},{"code_sha256_prefix":"972b9f317f5321f0","entry":"expand","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"972b9f317f5321f0"}},{"code_sha256_prefix":"152f75c9b44ec04e","entry":"expand","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"152f75c9b44ec04e"}},{"code_sha256_prefix":"4fd1ea2325d783a5","entry":"get_next_steps_expand","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"4fd1ea2325d783a5"}},{"code_sha256_prefix":"a6cb18e8066512b4","entry":"get_next_steps_expand","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6cb18e8066512b4"}},{"code_sha256_prefix":"921b11d38034e3e8","entry":"greedyPolicy","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"921b11d38034e3e8"}},{"code_sha256_prefix":"5eb7f8be714f63db","entry":"greedyPolicy","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5eb7f8be714f63db"}},{"code_sha256_prefix":"f2cd3cffcc558e0c","entry":"randomPolicy","repo":"THUDM/ReST-MCTS","repo_kind":"official","path":"MCTS/mcts.py","file_url":"https://github.com/THUDM/ReST-MCTS/blob/HEAD/MCTS/mcts.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":"f2cd3cffcc558e0c"}},{"code_sha256_prefix":"735d77158ce66113","entry":"randomPolicy","repo":"DIRECT-BIT/SRA-MCTS","repo_kind":"listed","path":"MCTS/mcts.py","file_url":"https://github.com/DIRECT-BIT/SRA-MCTS/blob/HEAD/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"735d77158ce66113"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}