{"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/deepseek-prover-v1-5-harnessing-proof","title":"DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search","arxiv_id":"2408.08152","date":"2024-08-15","proceeding":null,"authors":["Huajian Xin","Z. Z. Ren","Junxiao Song","Zhihong Shao","Wanjia Zhao","Haocheng Wang","Bo Liu","Liyue Zhang","Xuan Lu","Qiushi Du","Wenjun Gao","Qihao Zhu","Dejian Yang","Zhibin Gou","Z. F. Wu","Fuli Luo","Chong Ruan"],"abstract":"We introduce DeepSeek-Prover-V1.5, an open-source language model designed for theorem proving in Lean 4, which enhances DeepSeek-Prover-V1 by optimizing both training and inference processes. Pre-trained on DeepSeekMath-Base with specialization in formal mathematical languages, the model undergoes supervised fine-tuning using an enhanced formal theorem proving dataset derived from DeepSeek-Prover-V1. Further refinement is achieved through reinforcement learning from proof assistant feedback (RLPAF). Beyond the single-pass whole-proof generation approach of DeepSeek-Prover-V1, we propose RMaxTS, a variant of Monte-Carlo tree search that employs an intrinsic-reward-driven exploration strategy to generate diverse proof paths. DeepSeek-Prover-V1.5 demonstrates significant improvements over DeepSeek-Prover-V1, achieving new state-of-the-art results on the test set of the high school level miniF2F benchmark ($63.5\\%$) and the undergraduate level ProofNet benchmark ($25.3\\%$).","url_abs":"https://arxiv.org/abs/2408.08152v1","url_pdf":"https://arxiv.org/pdf/2408.08152v1.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":"deepseek-prover-v1-5-harnessing-proof","repo_url":"https://github.com/deepseek-ai/deepseek-prover-v1.5","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deepseek-prover-v1-5-harnessing-proof","repo_url":"https://github.com/augustepoiroux/LeanInteract","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automated-theorem-proving","task_name":"Automated Theorem Proving"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"monte-carlo-tree-search","method_name":"Monte-Carlo Tree Search"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","task":"Automated Theorem Proving","dataset":"miniF2F-test","model":"DeepSeek-Prover-V1.5","rank_in_archive_order":3,"of":29,"metrics":{"ITP":"Lean","Pass@32":"50.0","Pass@64":"50.7","cumulative":"63.5"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.08152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08152"}},"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/deepseek-ai/deepseek-prover-v1.5","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/augustepoiroux/LeanInteract","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1},"listed":{"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":"ff8bbf72d7f2fdcc","entry":"get_project_lean_version","repo":"augustepoiroux/LeanInteract","repo_kind":"listed","path":"src/lean_interact/utils.py","file_url":"https://github.com/augustepoiroux/LeanInteract/blob/HEAD/src/lean_interact/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff8bbf72d7f2fdcc"}},{"code_sha256_prefix":"f576abc866b698be","entry":"get_total_memory_usage","repo":"augustepoiroux/LeanInteract","repo_kind":"listed","path":"src/lean_interact/utils.py","file_url":"https://github.com/augustepoiroux/LeanInteract/blob/HEAD/src/lean_interact/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f576abc866b698be"}},{"code_sha256_prefix":"553538799f029812","entry":"message_intersects_code","repo":"augustepoiroux/LeanInteract","repo_kind":"listed","path":"src/lean_interact/interface.py","file_url":"https://github.com/augustepoiroux/LeanInteract/blob/HEAD/src/lean_interact/interface.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"553538799f029812"}},{"code_sha256_prefix":"eda86991d7c9e040","entry":"parse_lean_version","repo":"augustepoiroux/LeanInteract","repo_kind":"listed","path":"src/lean_interact/utils.py","file_url":"https://github.com/augustepoiroux/LeanInteract/blob/HEAD/src/lean_interact/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eda86991d7c9e040"}},{"code_sha256_prefix":"77994fb797e63cb3","entry":"cot_prompt","repo":"deepseek-ai/deepseek-prover-v1.5","repo_kind":"official","path":"prover/utils.py","file_url":"https://github.com/deepseek-ai/deepseek-prover-v1.5/blob/HEAD/prover/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77994fb797e63cb3"}},{"code_sha256_prefix":"4222bbd6373963f5","entry":"extract_positions","repo":"deepseek-ai/deepseek-prover-v1.5","repo_kind":"official","path":"prover/lean/ast_parser.py","file_url":"https://github.com/deepseek-ai/deepseek-prover-v1.5/blob/HEAD/prover/lean/ast_parser.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4222bbd6373963f5"}},{"code_sha256_prefix":"20ac111c42889614","entry":"extract_vals","repo":"deepseek-ai/deepseek-prover-v1.5","repo_kind":"official","path":"prover/lean/ast_parser.py","file_url":"https://github.com/deepseek-ai/deepseek-prover-v1.5/blob/HEAD/prover/lean/ast_parser.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"20ac111c42889614"}},{"code_sha256_prefix":"23c78fbc0be837a2","entry":"non_cot_few_shot_prompt","repo":"deepseek-ai/deepseek-prover-v1.5","repo_kind":"official","path":"prover/utils.py","file_url":"https://github.com/deepseek-ai/deepseek-prover-v1.5/blob/HEAD/prover/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23c78fbc0be837a2"}},{"code_sha256_prefix":"e4ed28dc52c5179d","entry":"non_cot_prompt","repo":"deepseek-ai/deepseek-prover-v1.5","repo_kind":"official","path":"prover/utils.py","file_url":"https://github.com/deepseek-ai/deepseek-prover-v1.5/blob/HEAD/prover/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4ed28dc52c5179d"}},{"code_sha256_prefix":"789c40fc9b050fa1","entry":"process_lean_file","repo":"deepseek-ai/deepseek-prover-v1.5","repo_kind":"official","path":"prover/lean/ast_parser.py","file_url":"https://github.com/deepseek-ai/deepseek-prover-v1.5/blob/HEAD/prover/lean/ast_parser.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"789c40fc9b050fa1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}