Lean Theorem Proving

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 86

All topics

ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
May 21, 2026Riyaz Ahuja, Tate Rowney, Jeremy Avigad +1LLM Self-Refinement Automated Theorem Proving
Carnegie Mellon University
Lean-GAP: A Dataset of Formalized Graduate Algebra Problems
May 20, 2026Seewoo Lee, Byung-Hak Hwang, Hyojae Lim +10Mathematical Reasoning Benchmarks Formal Verification
KAIST · Ethereum Foundation
Using Aristotle API for AI-Assisted Theorem Proving in Lean 4: A Formalisation Case Study of the Grasshopper Problem
May 19, 2026Gabriel Rongyang LauMathematical Reasoning Lean Theorem Proving
Nanyang Technological University, Singapore
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
May 18, 2026Jialin Lu, Soonho Kong, Rodrigo Stehling +4Large Language Model-Guided Optimization Lean Theorem Proving
Simon Fraser University · Amazon Web Services · MiroMind +1
OProver: A Unified Framework for Agentic Formal Theorem Proving
May 17, 2026David Ma, Kaijing Ma, Shawn Guo +7Automated Theorem Proving Lean Theorem Proving
M-A-P
CAM-Bench: A Benchmark for Computational and Applied Mathematics in Lean
May 17, 2026Wentao Long, Yunfei Zhang, Chenyi Li +3Mathematical Reasoning Benchmarks Benchmark Construction
Fudan University · Qingdao University · Peking University +1
Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics
May 13, 2026Moritz Firsching, Paul Lezeau, Salvatore Mercuri +8Mathematical Reasoning Benchmarks Automated Theorem Proving
Google DeepMind · Imperial College London · Stockholms universitet +1
LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
May 13, 2026Guoxiong Gao, Zeming Sun, Jiedong Jiang +5Lean Theorem Proving Evidence Retrieval
School of Mathematical Sciences, Peking University · 2IQuest Research · 3Research Institute for Mathematical Sciences, Kyoto University +5
Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving
May 12, 2026Shuo Xu, Jiakun Zhang, Junyu Lai +2Supervised Fine-Tuning Automated Theorem Proving
State Key Laboratory for Novel Software Technology, Nanjing University, China
FormalRewardBench: A Benchmark for Formal Theorem Proving Reward Models
May 11, 2026Zeynel A. Uluşan, Burak S. Akbudak, Can S. Erer +1Reward Modeling Automated Theorem Proving
Koç University, Department of Computer Science and Engineering · Codeway Studios · Bo˘gaziçi University, Department of Computer Engineering +1
Automated Formal Proofs of Combinatorial Identities via Wilf-Zeilberger Guidance and LLMs
May 6, 2026Beibei Xiong, Hangyu Lv, Junqi Liu +5Automated Theorem Proving Lean Theorem Proving
School of Software Engineering, East China Normal University, Shanghai, China · Institute of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China · School of Computer and Information Engineering, Henan University, Kaifeng, China
Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game
May 1, 2026Lixing LiMathematical Reasoning Benchmarks Lean Theorem Proving
St Anne’s College, Oxford, OX26HS, United Kingdom
OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
Apr 26, 2026Chenyi Li, Yanchen Nie, Zhenyu Ming +3Continual Learning for LLMs Automated Theorem Proving
School of Mathematical Sciences, Peking University · 2Huawei Technologies · Center for Machine Learning Research, Peking University +1
Benchmarking Testing in Automated Theorem Proving
Apr 26, 2026Jongyoon Kim, Hojae Han, Seung-won HwangLLM Evaluation Automated Theorem Proving
Interdisciplinary Program in Artificial Intelligence, Seoul National University1 · Electronics and Telecommunications Research Institute2
Progress in Formalizing Sphere Packing in Dimension 8
Apr 25, 2026Sidharth Hariharan, Christopher Birkbeck, Seewoo Lee +4Formal Verification Lean Theorem Proving
Carnegie Mellon University, Pittsburgh PA 15213, United States of America · University of East Anglia, Norwich NR4 7TJ, United Kingdom · University of California, Berkeley, Berkeley CA 94720, United States of America +4
Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization
Apr 25, 2026William Feng, Ethan Lou, Aryan SharmaLean Theorem Proving Code Generation Evaluation
Yale University, New Haven, Connecticut, USA.
Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning
Apr 21, 2026Kyuhee Kim, Auguste Poiroux, Antoine BosselutFormal Verification Lean Theorem Proving
EPFL
Yanasse: Finding New Proofs from Deep Vision's Analogies, Part 1
Apr 19, 2026Alexandre LinharesAutomated Theorem Proving Analogical Reasoning
Getulio Vargas Foundation · ARGO LABS
Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4
Apr 17, 2026Chengwu Liu, Yichun Yin, Ye Yuan +7Automated Theorem Proving Lean Theorem Proving
State Key Laboratory for Multimedia Information Processing, School of Computer Science, PKU-Anker LLM Lab, Peking University · Huawei Technologies Co., Ltd. · School of Software & Microelectronics, Peking University +1
Understanding Tool-Augmented Agents for Lean Formalization: A Factorial Analysis
Apr 16, 2026Ke Zhang, Patricio Gallardo, Maziar Raissi +1Code Translation LLM Agent Evaluation
University of California, Riverside.
Nazrin: An Atomic Neural Proof Automation Tactic in Lean 4
Feb 21, 2026Leni Aniva, Iori Oikawa, David Dill +1Automated Theorem Proving Lean Theorem Proving
Stanford University, Stanford, U.S. · Northeastern University, Massachusetts, U.S. · Stanford University
VeriSoftBench: Repository-Scale Formal Verification Benchmarks for Lean
Feb 20, 2026Yutong Xin, Qiaochu Chen, Greg Durrett +1LLM Evaluation Formal Verification
The University of Texas at Austin · New York University
Inference-Time Diversity in RL-Trained Lean Theorem Provers: A Diagnostic Study
Jan 22, 2026Zachary BurtonInference-Time Search RL for Language Model Reasoning
Massachusetts Institute of Technology, Cambridge, MA, USA.
Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph
Oct 6, 2025Hanyu Wang, Ruohan Xie, Yutong Wang +3Lean Theorem Proving Autoformalization
Peking University · Institute for Artificial Intelligence, Peking University · IQuest Research +4
Discovering New Theorems via LLMs with In-Context Proof Learning in Lean
Sep 16, 2025Kazumi Kasaura, Naoto Onda, Yuta Oriike +3Automated Theorem Proving In-Context Learning
OMRON SINIC X Corporation · RIKEN AIP · AutoRes +7
Formally Solving Answer-Construction Problems in Lean
May 24, 2025Jialiang Sun, Yuzhi Tang, Ao Li +2Lean Theorem Proving LLM Mathematical Reasoning
University of Toronto, Toronto, Canada · Georgia Institute of Technology, Atlanta, USA

May 21, 2026, cs.AIJ/K move · Enter open · S save

ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization

Riyaz Ahuja, Tate Rowney, Jeremy Avigad, Sean Welleck

Carnegie Mellon University

LLM Self-Refinement Automated Theorem Proving Lean Theorem Proving Neuro-Symbolic Reasoning

Open paper AskPDF arXiv

Formal mathematics libraries are rapidly expanding, creating a growing need to refactor verified proofs for maintainability and to improve training data quality for neural provers. However, scalable proof optimization is hindered by heterogeneous and heuristically specified objectives, scarce data, and high training and inference costs. To overcome these challenges, we introduce ImProver 2, a neurosymbolic framework for automated proof optimization in Lean 4. ImProver 2 combines a data-efficient expert-iteration pipeline with a scaffold that exposes formal structure alongside lightweight informal abstractions. We further introduce a suite of metrics capturing structural proof properties. Using ImProver 2, we train a 7B-parameter model that outperforms orders-of-magnitude larger models within the same model family, and is competitive with mid-tier frontier models across metrics. We additionally demonstrate that our neurosymbolic scaffold significantly improves performance across both small and frontier models. We show that with proper scaffolding and training, small models can effectively restructure research-level proofs over complex and varied metrics, matching substantially larger systems and establishing proof optimization as a scalable, learnable task.

Momentum

Related topics

Latest papers 86