paper-with-me

Papers

Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving

2025-05-07 · Qi Liu, Xinhao Zheng, Renqiu Xia, Xingzhi Qi, Qinxiang Cao, Junchi Yan

As a seemingly self-explanatory task, problem-solving has been a significant component of science and engineering. However, a general yet concrete formulation of problem-solving itself is missing. With the recent development of AI-based problem-solving agents, the demand for process-level verifiability is rapidly increasing yet underexplored. To fill these gaps, we present a principled formulation of problem-solving as a deterministic Markov decision process; a novel framework, FPS (Formal Problem-Solving), which utilizes existing FTP (formal theorem proving) environments to perform process-verified problem-solving; and D-FPS (Deductive FPS), decoupling solving and answer verification for better human-alignment. The expressiveness, soundness and completeness of the frameworks are proven. We construct three benchmarks on problem-solving: FormalMath500, a formalization of a subset of the MATH500 benchmark; MiniF2F-Solving and PutnamBench-Solving, adaptations of FTP benchmarks MiniF2F and PutnamBench. For faithful, interpretable, and human-aligned evaluation, we propose RPE (Restricted Propositional Equivalence), a symbolic approach to determine the correctness of answers by formal verification. We evaluate four prevalent FTP models and two prompting methods as baselines, solving at most 23.77% of FormalMath500, 27.47% of MiniF2F-Solving, and 0.31% of PutnamBench-Solving.

📄 PDF Abstract BibTeX arXiv:2505.04528

Code (0)

등록된 구현이 없습니다.

Tasks

Automated Theorem Proving

Similar Papers 제목 키워드 기반

MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalize

2026-08-26 · Jiaxin Yuan, Connor Martinez Lockhart, Xiaoyu Liu, Jiaqi Wang 외 arxiv

Formal theorem proving enables machine-verifiable evaluation of mathematical reasoning, yet existing benchmarks often emphasize aggregate proof accuracy, concentrate on a narrow range of mathematics, and provide limited …

Mathematical Reasoning

TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib?

2026-03-13 · Alexander K Taylor, Junyi Zhang, Ethan Ji, Vigyan Sahai 외 arxiv

Automated theorem proving (ATP) benchmarks largely consist of problems formalized in MathLib, so current ATP training and evaluation are heavily biased toward MathLib's definitional framework. However, frontier mathemati…

Automated Theorem Proving

TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics

2026-06-08 · QuocViet Pham, Elvir Karimov, Andrey Galichin, Ivan Oseledets arxiv

LLMs have recently achieved strong results on formal proving benchmarks. However, existing evaluations remain heavily concentrated on competition-style problems and often fail to capture how models behave on longer, more…

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

Weighted universal approximation of differentiable maps on infinite-dimensional manifolds

2026-06-08 · Philipp Schmocker, Josef Teichmann arxiv

We generalize the universal approximation theorem for functional input neural networks (FNN) to differentiable maps by including the approximation of the derivatives. A FNN maps the input from a possibly infinite-dimensi…