paper-with-me

홈 › Papers

VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving

2026-06-17 · Manish Acharya, Zhenyu Liao, Yueke Zhang, Kevin Leach, Yu Huang, Yifan Zhang arxiv

LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit. We present VERITAS, a zero-shot framework that routes every verifier signal back into proof search through a two-phase protocol: Best-of-N sampling first, then a critic-guided MCTS pass that ingests Phase 1 failures as explicit negative examples. The protocol preserves every theorem solved by its own Phase 1 sweep, so Phase 2's additional solves are attributable to feedback-driven exploration. VERITAS reaches 40.6% on miniF2F (vs. an independently run Best-of-5 at 36.9%, Portfolio 26.2%) and 7.3% on VERITAS-CombiBench, a 55-theorem combinatorics benchmark we release on which Best-of-5 (1.8%) falls below Portfolio (3.6%), exposing that unguided sampling hurts when correct lemma names must be recovered iteratively from verifier feedback. Artifacts are available on GitHub.

📄 PDF Abstract BibTeX arXiv:2606.19399

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generating Natural Language Proofs with Verifier-Guided Search

2022-05-25 · Kaiyu Yang, Jia Deng, Danqi Chen

Reasoning over natural language is a challenging problem in NLP. In this work, we focus on proof generation: Given a hypothesis and a set of supporting facts, the model generates a proof tree indicating how to derive the…

Hallucinationvalid

ProofNet++: A Neuro-Symbolic System for Formal Proof Verification with Self-Correction

2025-05-30 · Murari Ambati

We propose ProofNet++, a neuro-symbolic framework that enhances automated theorem proving by combining large language models (LLMs) with formal proof verification and self-correction mechanisms. Current LLM-based systems…

Automated Theorem Proving

Automating Formal Verification with Reinforcement Learning and Recursive Inference

2026-05-29 · Max Tan arxiv

Automated formal verification remains challenging for large language models because data for proof assistants and verification-aware languages is scarce, and correctness depends on satisfying precise machine-checkable sp…

Reinforcement Learning

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 외 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 verifica…

Zero-Shot Verification-guided Chain of Thoughts

2025-01-21 · Jishnu Ray Chowdhury, Cornelia Caragea

Previous works have demonstrated the effectiveness of Chain-of-Thought (COT) prompts and verifiers in guiding Large Language Models (LLMs) through the space of reasoning. However, most such studies either use a fine-tune…