Overview

Automated theorem proving studies how to turn goals and assumptions into proofs that trusted checkers can validate, supporting dependable mathematics and software verification. Approaches range from symbolic search, resolution, tableaux, SAT/SMT solving, and tactics to language models that retrieve lemmas, decompose goals, learn from proof traces, and use Lean, Rocq, Isabelle, or Dafny feedback. Evaluation spans contest benchmarks such as miniF2F and PutnamBench, large proof libraries, code-verification tasks, and research-level problems. A central challenge is moving from benchmark success to robust, economical proofs whose formal statements faithfully capture the intended mathematics or specifications; autoformalization and semantic verification remain difficult.

Latest papers

CardsList

174 papers18 papers in the last four weeks, down 36% on the four weeks before. 0.1% of all new papers.

  1. ProofCoder: Continuous Reasoning for Automated Software Verification

    Nov 10, 2026Martim Afonso, Inês Lynce, Maurizio Morisio +1Large Language Model-Guided Theorem ProvingAutomated Theorem Proving

  2. Statopia: A Prover--Library Ecosystem for Automated Formalization and Proof Discovery in Statistics

    Nov 8, 2026Ziyuan Chen, Tong Gan, Wei Zhang +4Automated Theorem ProvingAutoformalization

  3. LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation

    Nov 5, 2026Hang Zhang, Qihao Ye, Litong Liu +7Large Language Model-Guided Theorem ProvingAutomated Theorem Proving

  4. TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research

    Nov 5, 2026Yifan Luo, Zhengying Liu, Yang Yuan +2Language Model Reasoning EvaluationAI Agent Benchmarks

  5. Autonomous AI Agents Systematically Diverge From Human Preferences in Proof Formalization

    Nov 4, 2026Bálint Gyevnár, Simon DeDeoHuman-AI CollaborationPreference Alignment

  6. TLAPS-Bench: Formally Proving Correctness of Real-World System Specifications with TLA+ Proof System

    Nov 2, 2026Qian Cheng, Ruize Tang, Saad Mohammad Rafid Pial +13Automated Theorem ProvingLarge Language Model-Guided Theorem Proving

  7. Reap: Uncovering Monte Carlo proof search with a lightweight model

    Nov 2, 2026Yutong Wang, Xuanzhi Ren, Tianyi Xu +5Automated Theorem ProvingLarge Language Model-Guided Theorem Proving

  8. Automated Theorem Generation in First-Order Logic by Construction from Triangular Standard Contradictions

    Oct 30, 2026Yang Xu, Shuwei Chen, Hailin Guo +1First-Order LogicLogical Reasoning

  9. Algebraic World Model: From Exploration to Proofs

    Oct 29, 2026Guancheng Pan, Qixin Tan, Yang Yuan +1ARC-AGIAutomated Theorem Proving

  10. Hammering with Vampire in Lean

    Oct 29, 2026Jonas Bodingbauer, Laura KovácsAutomated Theorem ProvingLean Theorem Proving

  11. Can LLMs Reliably Grade Olympiad Proofs? A Study of Mathematical Verification with LLMs

    Oct 27, 2026Azim Ospanov, Zijin Feng, Ding Ding +5Automated GradingLanguage Model Reasoning Evaluation

  12. KAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents

    Oct 26, 2026Zihua She, Xiao WangLarge Language Model-Guided Theorem ProvingAutomated Theorem Proving

  13. Efficient Proof Generation for Lean Statements with Multiple Candidate Answers

    Oct 25, 2026Pengzhen Lin, Ke Zhang, Maziar Raissi +1Automated Theorem ProvingLLM Mathematical Reasoning

  14. h1: A Taste of the Bitter Lesson in Automated Theorem Proving

    Oct 25, 2026Skander Moalla, Ahmad Rammal, Niket Patel +2Large Language Model-Guided Theorem ProvingAutomated Theorem Proving

  15. PACE: Research Proving Agent for Adaptive Conjecture Exploration

    Oct 24, 2026Shu Miao, Feiming Wang, Wentao Long +3AI-Assisted Mathematical DiscoveryAutonomous Research Agents

  16. ReuF2F: Benchmarking Coding Agents on Formalized Undergraduate Research Problems

    Oct 19, 2026Zeyu Zheng, Yiyang Liu, Yuyang Zhao +20Coding Agent BenchmarksMathematical Reasoning Benchmarks

  17. Lean Graph Search for Formal Theorem Proving

    Oct 15, 2026Yihan Xu, Jia-Chen Gu, Junyi Zhang +7Graph-Based RetrievalLean Theorem Proving

  18. Reset Early, Reset Often, Eliminate Models

    Oct 13, 2026Martin S. Fixman, Fredrik Rømming, Sean B. HoldenAutomated Theorem Proving

  19. Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean

    Oct 12, 2026Tomas Ortega, Simon Park, Ayush Khaitan +3Large Language Model-Guided Theorem ProvingAutomated Theorem Proving

  20. TLA-Verus: Generating and Solving Temporal Proof Obligations with LLM Agents

    Oct 10, 2026Kseniia Strelbytska, Balázs Szilágyi, Anna Mészáros +1Formal VerificationAutomated Theorem Proving

  21. SqueezeBench: Saturation-Resilient Evaluation of Mathematical Capability

    Oct 9, 2026Pablo Manrique, Hai Xia, Stefan SzeiderMathematical Reasoning BenchmarksBenchmark Design

  22. LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs

    Oct 8, 2026Nihal Jain, Shuangjie Yao, Begum Cicekdag +2Automated Theorem ProvingInference-Time Search

  23. NanoProof: Open and Efficient Automated Theorem Proving in Lean 4

    Oct 8, 2026Matěj Kripner, Milan StrakaAutomated Theorem ProvingLean Theorem Proving

  24. Bolzano: From Expert-Guided Proof Search to Automated Open-Problem Solving

    Oct 7, 2026Adrián Zámečník, Matěj Kripner, Martin Koutecký +5Automated Theorem ProvingAI Agents for Scientific Discovery

  25. Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification

    Oct 7, 2026Shuangjie Yao, Nikolaus Holzer, Mark Paul Santolucito +3Automated Theorem ProvingFormal Verification