Papers › DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning...

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

15 Aug 2024arXiv:2408.08152archive 2025-07-28

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

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%).

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 6 ran (4 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 4 ran (2 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

deepseek-ai/deepseek-prover-v1.5 officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (2 instrument-failed) · 0 unverified report
augustepoiroux/LeanInteract mentioned on GitHubMITSyntology: 4 samples, 4 ran (2 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
4ran

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

deepseek-ai/deepseek-prover-v1.5 official repository 6 samples, 6 ran (2 instrument-failed) · 0 unverified
cot_prompt prover/utils.py ran · our draft was wrong MIT (permissive) · 77994fb797e63cb3 · report fixture: signature data:dict/0/? · returned str · level recorded 2026-09-25
extract_positions prover/lean/ast_parser.py ran · honoured contract MIT (permissive) · 4222bbd6373963f5 · report fixture: signature node:dict/0/? · returned list · level recorded 2026-09-25
extract_vals prover/lean/ast_parser.py ran · our draft was wrong MIT (permissive) · 20ac111c42889614 · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-25
non_cot_few_shot_prompt prover/utils.py ran MIT (permissive) · 23c78fbc0be837a2 · report fixture: signature data:dict/0/? · returned str · level recorded 2026-09-25
non_cot_prompt prover/utils.py ran MIT (permissive) · e4ed28dc52c5179d · report fixture: signature data:dict/0/? · returned str · level recorded 2026-09-25
process_lean_file prover/lean/ast_parser.py ran MIT (permissive) · 789c40fc9b050fa1 · report fixture: signature file_contents:str/0/str, byte_idx_1:int/0/int, byte_idx_2:int/0/int · returned tuple · level recorded 2026-09-25
augustepoiroux/LeanInteract community (archive-listed) 4 samples, 4 ran (2 instrument-failed) · 0 unverified
get_project_lean_version src/lean_interact/utils.py ran · our draft was wrong MIT (permissive) · ff8bbf72d7f2fdcc · report fixture: signature project_dir:PosixPath/0/? · returned str · level recorded 2026-09-24
get_total_memory_usage src/lean_interact/utils.py ran · honoured contract MIT (permissive) · f576abc866b698be · report fixture: signature proc:Process/0/? · returned int · level recorded 2026-09-24
message_intersects_code src/lean_interact/interface.py ran MIT (permissive) · 553538799f029812 · report fixture: signature msg:Message/0/?, start_pos:Pos/0/?, end_pos:Pos/0/? · returned bool · level recorded 2026-09-24
parse_lean_version src/lean_interact/utils.py ran · our draft was wrong MIT (permissive) · eda86991d7c9e040 · report fixture: signature lean_version:str/0/str · returned str · level recorded 2026-09-24

Tasks

Automated Theorem ProvingLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Automated Theorem Proving miniF2F-test DeepSeek-Prover-V1.5 ITP Lean #3 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-test DeepSeek-Prover-V1.5 Pass@32 50.0 #3 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-test DeepSeek-Prover-V1.5 Pass@64 50.7 #3 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-test DeepSeek-Prover-V1.5 cumulative 63.5 #3 of 29 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Monte-Carlo Tree SearchSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections