Overview

Autoformalization translates informal mathematical statements, proofs, and software or scientific requirements into forms that proof assistants and solvers can check. Systems commonly combine language models with library retrieval, dependency-aware decomposition, and iterative feedback from Lean or Isabelle checkers, provers, model checkers, and tests. Benchmarks span competition and textbook mathematics, first-order logic, and executable software specifications, while agentic workflows increasingly tackle larger theories and research developments. The central challenge is semantic faithfulness: a formal artifact can compile or verify while misstating its source, so evaluation increasingly combines execution with equivalence checks, adversarial tests, and human review.

Latest papers

CardsList

124 papers12 papers in the last four weeks, down 25% on the four weeks before. 0.1% of all new papers.

  1. Sage: Formalization with Semantic Correction

    Sep 16, 2026Thomas Hirtz, Farzad Jafarrahmani, Abdelmouksit Sagueni +3LLM Self-CorrectionLean Theorem Proving

  2. Autoformalizing Argumentative Material Inferences

    Sep 15, 2026Xin Quan, Reto Gubelmann, André FreitasLogical ReasoningInteractive Theorem Proving

  3. Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification

    Sep 10, 2026Joshua Ong Jun Leang, Haonan Li, Zheng Zhao +6Automated Theorem ProvingAgentic Reasoning

  4. Beyond Solver Verdicts: Generative Reward Models for Autoformalization

    Sep 10, 2026Vikash Singh, Debargha Ganguly, Aman Goel +5Reward ModelingFormal Verification

  5. AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics

    Sep 4, 2026Weichen Winston Yin, Jacob M. Taylor, Dirk R. Englund +1AutoformalizationAutomated Theorem Proving

  6. SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization

    Aug 29, 2026Hojae Han, Jongyoon Kim, Sanghyeok Park +8Autoformalization

  7. NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry

    Aug 28, 2026Samuel Xiao, Judy Song, Rory Hu +1AutoformalizationLLM Evaluation

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

    Aug 26, 2026Jiaxin Yuan, Udari Madhushani Sehwag, Connor Martinez Lockhart +13Mathematical Reasoning BenchmarksAutomated Theorem Proving

  9. Does the Proof Prove It That Way? Faithful Formalization of Elements Proofs

    Aug 15, 2026Tadd Mao, Tianjun Zhong, Dhruva Arekar +5Automated Theorem ProvingReasoning Verification

  10. FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation

    Aug 11, 2026Rob Cornish, Iacopo Ghinassi, Po-Hung Yeh +7CoT FaithfulnessLLM Sycophancy

  11. MechGeo: Autoformalizing and Proving Euclidean Geometry in Lean 4

    Aug 3, 2026Hao Shen, Junyu Guo, Tian Cui +2Automated Theorem ProvingLean Theorem Proving

  12. Specula: Scaling formal specifications for autonomous model checking of system code

    Jul 28, 2026Qian Cheng, Saad Mohammad Rafid Pial, Ruize Tang +6Software Engineering AgentsFormal Verification

  13. TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation

    Jul 26, 2026Arslan Bisharat, Eric Spencer, Brian Ortiz +8LLM EvaluationFormal Verification

  14. Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study

    Jul 23, 2026Yan Huang, Xubing Hao, Xiaojin Li +4AutoformalizationClinical NLP

  15. Faithful Autoformalization of Natural Language Assertions

    Jul 14, 2026Hongyi Liu, Madhusudan Parthasarathy, Adithya MuraliAutomated Software TestingLLM-Based Program Synthesis

  16. Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases

    Jul 14, 2026Marcus J. Min, Mike He, Zhaoyu Li +5Autoformalization

  17. Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization

    Jul 13, 2026Tian-Shuo Liu, Shiyuan Zhang, Zijie Geng +5Test-Time OptimizationAutoformalization

  18. Multi-agent Autoformalization of Tensor Network Theory

    Jul 8, 2026Sirui Lu, Erickson Tjoa, J. Ignacio CiracTensor NetworksMulti-Agent LLM Systems

  19. FormalRx: Rectify and eXamine Semantic Failures in Autoformalization

    Jul 6, 2026Haocheng Wang, Baiyu Huang, Yingjia Wan +4Automated EvaluationAutoformalization

  20. Reformalization of the Jordan Curve Theorem

    Jul 2, 2026Simon Guilloud, Sankalp Gambhir, Samuel ChassotInteractive Theorem ProvingAutoformalization

  21. Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization

    Jun 30, 2026Ke Zhang, Patricio Gallardo Candela, Sudhir Murthy +3LLM-as-a-JudgeLean Theorem Proving

  22. Translating Natural Language to Strategic Temporal Specifications via LLMs

    Jun 29, 2026Marco Aruta, Francesco Improta, Vadim Malvone +2Formal VerificationMulti-Agent Systems

  23. The Signal-Coverage Matrix: Stratifying Type and Semantic Errors in Statement Autoformalization

    Jun 26, 2026Chengxiao Dai, Zhaokun Yan, Zhanhui LinLLM Self-CorrectionLean Theorem Proving

  24. Theory-Scale Auto-Formalization of Logics for Computer Science

    Jun 25, 2026Yuming Feng, Frederick Pu, One An +5Automated Theorem ProvingLean Theorem Proving