paper-with-me

홈 › Papers

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

2024-08-15 · 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 ($25.3\%$).

📄 PDF Abstract BibTeX arXiv:2408.08152

Code (2)

deepseek-ai/deepseek-prover-v1.5 공식 구현 pytorch
augustepoiroux/LeanInteract

Tasks

Automated Theorem ProvingLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Monte-Carlo Tree Search Monte-Carlo Tree Search is a planning algorithm that accumulates value estimates obtained from Monte Carlo simulations in order to successively direct simulations towards more…

Similar Papers 제목 키워드 기반

Process-Verified Reinforcement Learning for Theorem Proving via Lean

2026-06-18 · Minsu Kim, Se-Young Yun arxiv

While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, fine-grained structured feedback. This ga…

Reinforcement Learning

Prover Agent: An Agent-based Framework for Formal Mathematical Proofs

2025-06-24 · Kaito Baba, Chaoran Liu, Shuhei Kurita, Akiyoshi Sannai

We present Prover Agent, a novel AI agent for automated theorem proving that integrates large language models (LLMs) with a formal proof assistant, Lean. Prover Agent coordinates an informal reasoning LLM, a formal prove…

AI AgentAutomated Theorem ProvingMathematical Proofs

Abduction Prover in Isabelle/HOL

2026-06-03 · Yutaka Nagashima, Daniel Sebastian Goc arxiv

Proof assistants based on expressive logics suffer limited automation for proof search, raising the cost of formal verification based on proof assistants. We address this problem by introducing the Abduction Prover for I…

Leanabell-Prover-V2: Verifier-integrated Reasoning for Formal Theorem Proving via Reinforcement Learning

2025-07-11 · Xingguang Ji, Yahui Liu, Qi Wang, Jingyuan Zhang 외 arxiv

We introduce our Leanabell-Prover-V2, a 7B large language models (LLMs) that can produce formal theorem proofs in Lean 4, with verifier-integrated Long Chain-of-Thoughts (CoT). Following our previous work Leanabell-Prove…

Reinforcement Learning

StepFun-Prover Preview: Let's Think and Verify Step by Step

2025-07-27 · Shijie Shang, Ruosi Wan, Yue Peng, Yutong Wu 외 arxiv

We present StepFun-Prover Preview, a large language model designed for formal theorem proving through tool-integrated reasoning. Using a reinforcement learning pipeline that incorporates tool-based interactions, StepFun-…

Automated Theorem ProvingReinforcement Learning