paper-with-me

Papers

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

2026-06-11 · Jiacheng Chen, Xinyu Zhang, Shunkai Zhang, Yanmohan Wang, Lin Li, Tiancheng Qin, Qin Wang, Zhengmao Zhu, Tianle Li, Jingyang Li, Zehan Li, Binyang Jiang, Jin Zhu, Han Ding, Fei Yu, Chenyu Du, Zijian Song, Jiayuan Song, Zhi Zhang, Yunan Huang, Weiyu Cheng, Pengyu Zhao, Yu Cheng arxiv

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities -- proof generation, proof verification, and critique-conditioned proof repair -- using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

📄 PDF Abstract BibTeX arXiv:2606.13473

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection

2025-11-17 · Sadegh Mahdavi, Branislav Kisacanin, Shubham Toshniwal, Wei Du 외 arxiv

Large language models have achieved remarkable success on final-answer mathematical problems, largely due to the ease of applying reinforcement learning with verifiable rewards. However, the reasoning underlying these so…

Reinforcement Learning

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

2025-11-27 · Zhihong Shao, Yuxiang Luo, Chengda Lu, Z. Z. Ren 외 arxiv

Large language models have made significant progress in mathematical reasoning, which serves as an important testbed for AI and could impact scientific research if further advanced. By scaling reasoning with reinforcemen…

Reinforcement LearningMathematical Reasoning

Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math

2025-10-15 · Shrey Pandit, Austin Xu, Xuan-Phi Nguyen, Yifei Ming 외 arxiv

Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition, writing mathematical proofs where, to receive full credit, each step must be not only co…

Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

2026-07-07 · Jihao Liu, Guoxiong Gao, Zeming Sun, Bin Wu 외 arxiv

Recent LLM-based mathematical reasoning agents have begun to tackle research-level problems and, in several cases, have contributed to the resolution of open problems. However, scaling and orchestrating such agents effec…

Mathematical Reasoning

Towards Reliable Proof Generation with LLMs: A Neuro-Symbolic Approach

2025-05-20 · Oren Sultan, Eitan Stern, Dafna Shahaf

Large language models (LLMs) struggle with formal domains that require rigorous logical deduction and symbolic reasoning, such as mathematical proof generation. We propose a neuro-symbolic approach that combines LLMs' ge…