Image de couverture de livre

Distilling LLM Feedback for Lean Theorem Proving

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Narozniak, Gaetan, Biau, Gérard, Munos, Rémi, Rammal, Ahmad, Marion, Pierre
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Automatic Textbook Formalization
par: Gloeckle, Fabian, et autres
Publié: (2026)

LeanConjecturer: Automatic Generation of Mathematical Conjectures for Theorem Proving
par: Onda, Naoto, et autres
Publié: (2025)

Formalizing Mathematics at Scale
par: Rammal, Ahmad, et autres
Publié: (2026)

Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean
par: Song, Peiyang, et autres
Publié: (2024)

LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
par: Gao, Guoxiong, et autres
Publié: (2026)

LeanAgent: Lifelong Learning for Formal Theorem Proving
par: Kumarappan, Adarsh, et autres
Publié: (2024)

Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4
par: Liu, Chengwu, et autres
Publié: (2026)

Super-Exponential Regret for UCT, AlphaGo and Variants
par: Orseau, Laurent, et autres
Publié: (2024)

Proving Theorems Recursively
par: Wang, Haiming, et autres
Publié: (2024)

Lean-STaR: Learning to Interleave Thinking and Proving
par: Lin, Haohan, et autres
Publié: (2024)

LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction
par: George, Robert Joseph, et autres
Publié: (2025)

MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
par: Wang, Ruida, et autres
Publié: (2025)

Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
par: Quan, Xin, et autres
Publié: (2025)

Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving
par: Xu, Shuo, et autres
Publié: (2026)

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
par: Arnal, Charles, et autres
Publié: (2025)

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
par: Zhang, Ziyin, et autres
Publié: (2025)

From LLM-Generated Conjectures to Lean Formalizations: Automated Polynomial Inequality Proving via Sum-of-Squares Certificates
par: Zuo, Ruobing, et autres
Publié: (2026)

A Minimal Agent for Automated Theorem Proving
par: Requena, Borja, et autres
Publié: (2026)

A Survey on Deep Learning for Theorem Proving
par: Li, Zhaoyu, et autres
Publié: (2024)

Physics-informed machine learning as a kernel method
par: Doumèche, Nathan, et autres
Publié: (2024)

BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving
par: Xin, Ran, et autres
Publié: (2025)

A Combinatorial Identities Benchmark for Theorem Proving via Automated Theorem Generation
par: Xiong, Beibei, et autres
Publié: (2025)

Lean Meets Theoretical Computer Science: Scalable Synthesis of Theorem Proving Challenges in Formal-Informal Pairs
par: Zhang, Terry Jingchen, et autres
Publié: (2025)

LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation
par: Lai, Junyu, et autres
Publié: (2025)

Aristotle: IMO-level Automated Theorem Proving
par: Achim, Tudor, et autres
Publié: (2025)

STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
par: Dong, Kefan, et autres
Publié: (2025)

Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models
par: Cao, Chenrui, et autres
Publié: (2025)

Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation
par: Wu, Shaonan, et autres
Publié: (2024)

Mathesis: Towards Formal Theorem Proving from Natural Languages
par: Xuejun, Yu, et autres
Publié: (2025)

Psychometric-Based Evaluation for Theorem Proving with Large Language Models
par: Zhang, Jianyu, et autres
Publié: (2025)

Steering LLMs for Formal Theorem Proving
par: Kirtania, Shashank, et autres
Publié: (2025)

Partial Label Learning for Automated Theorem Proving
par: Zombori, Zsolt, et autres
Publié: (2025)

PhysProver: Advancing Automatic Theorem Proving for Physics
par: Zhang, Hanning, et autres
Publié: (2026)

RLMEval: Evaluating Research-Level Neural Theorem Proving
par: Poiroux, Auguste, et autres
Publié: (2025)

Lyra: Orchestrating Dual Correction in Automated Theorem Proving
par: Zheng, Chuanyang, et autres
Publié: (2023)

Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving
par: Rashie, Devakh, et autres
Publié: (2026)

Learning to Reason with Insight for Informal Theorem Proving
par: Li, Yunhe, et autres
Publié: (2026)

HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement
par: Hu, Jilin, et autres
Publié: (2025)

OProver: A Unified Framework for Agentic Formal Theorem Proving
par: Ma, David, et autres
Publié: (2026)

FormalRewardBench: A Benchmark for Formal Theorem Proving Reward Models
par: Uluşan, Zeynel A., et autres
Publié: (2026)