Interactive Theorem Proving

Overview

Interactive theorem proving develops proofs inside systems such as Lean, Isabelle, Coq/Rocq, Agda, and EasyCrypt, where a small trusted kernel checks each result. Common approaches include tactic search, SMT and automated theorem prover integration, and language-model agents that formalize problems, propose proof steps, and revise them using proof-state or compiler feedback. Benchmarks such as miniF2F, Putnam problems, and software-verification suites test these methods, while textbook formalizations and interactive tools also support mathematical understanding and teaching. Automation is becoming more capable, but reliable performance on unfamiliar, multi-step problems remains difficult, and proof acceptance alone does not guarantee faithful assumptions, authorized edits, or usable proof structure.

Latest papers

CardsList

34 papers3 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

  1. Theorem prover Arend

    Oct 19, 2026Fedor Part, Valery Isaev, Sergey SinchukInteractive Theorem Proving

  2. Mathematical Proof Assistants for Teaching Logic: The LogiKEy Methodology

    Oct 6, 2026Christoph Benzmüller, David Fuenmayor, Luca PasettoLogical ReasoningInteractive Theorem Proving

  3. Growing an Agent/Prover Interface: Evolutionary Tool Design for Cost-Efficient Theorem Proving in Rocq and Lean

    Sep 30, 2026Jules Viennot, Guillaume Baudart, Marc LelargeAutomated Theorem ProvingEvolutionary Optimization

  4. Autoformalizing Argumentative Material Inferences

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

  5. Monadic Second-Order Logic in HOL: Deep and Shallow with Automated Faithfulness (Extended Preprint)

    Sep 7, 2026Christoph Benzmueller, Daniel KirchnerInteractive Theorem Proving

  6. Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt

    Sep 5, 2026Yupeng Ren, Zhaoxuan Li, Rui ZhangInteractive Theorem ProvingMultimodal Large Language Models

  7. CAPRI: Contract-Aware Proof Repair for Isabelle

    Aug 13, 2026Jim Woodcock, Gabriel Leite, Augusto Sampaio +1LLM AuditingInteractive Theorem Proving

  8. Can Open-Weight LLMs Produce Kernel-Verified Coq Proofs? A Pilot Study

    Aug 5, 2026Ahmed Ryan, Md Erfan, Akond Ashfaque Ur Rahman +1LLM EvaluationAutomated Theorem Proving

  9. Encoding Event-B Proof Rules in Prolog: An Interactive Sequent Prover for ProB

    Jul 23, 2026Katharina Engels, Jan Gruteser, Michael LeuschelAutomated Theorem ProvingInteractive Theorem Proving

  10. AoA: Theorem Proving Agent over Abstract Syntax Tree of Redesigned Language

    Jul 17, 2026Qiyuan Xu, Joshua Ong Jun Leang, Renxi Wang +4Large Language Model-Guided Theorem ProvingAutomated Theorem Proving

  11. MathCoPilot: An Interactive System for Human-AI Symbiotic Paradigm of Mathematical Research

    Jul 16, 2026Junjie Zhang, Jiayu Liu, Wenbin Liu +11Multi-Agent LLM SystemsAutomated Theorem Proving

  12. TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs

    Jul 13, 2026Burak S. Akbudak, Zeynel A. Uluşan, Can S. Erer +1Automated Theorem ProvingTree Search

  13. First-Order Modal Logic in HOL: Deep and Shallow Embeddings with Automated Faithfulness (Extended Preprint)

    Jul 12, 2026Christoph Benzmüller, Daniel KirchnerAutomated Theorem ProvingInteractive Theorem Proving

  14. OpenProver: Agentic and Interactive Theorem Proving with Lean 4

    Jul 10, 2026Matěj Kripner, Milan StrakaMulti-Agent LLM SystemsAutomated Theorem Proving

  15. From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

    Jul 8, 2026Eric Jiang, Xiao Liang, Yingjia Wan +17Automated Theorem ProvingInteractive Theorem Proving

  16. Reformalization of the Jordan Curve Theorem

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

  17. AXLE: A Cloud Infrastructure for Lean 4 Theorem Proving Utilities

    Jun 24, 2026Jimmy Xin, Alex Schneidman, Chris Cummins +3Interactive Theorem ProvingFormal Verification

  18. Abduction Prover in Isabelle/HOL

    Jun 3, 2026Yutaka Nagashima, Daniel Sebastian GocAutomated Theorem ProvingAbductive Reasoning

  19. Proof-Refactor: Refactoring Generated Formal Proofs into Modular Artifacts

    Jun 2, 2026Yiming Fu, Peixuan Liu, Zichen Wang +1Interactive Theorem ProvingLean Theorem Proving

  20. LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks

    Jun 2, 2026Po-Nien Kung, Linfeng Song, Dawsen Hwang +10Mathematical Reasoning BenchmarksLarge Language Model-Guided Theorem Proving

  21. Many Logics, One Methodology: A Plea for Logical Pluralism in Formalised Reasoning (preprint)

    May 26, 2026Christoph Benzmüller, Daniel Kirchner, Luca PasettoLogical ReasoningInteractive Theorem Proving

  22. Keep the Proof State Live: Snapshotting for Efficient Tactic Search in Lean 4

    May 25, 2026Austin Shen, Yunong ShiInference-Time SearchAutomated Theorem Proving

  23. Just Type It in Isabelle! AI Agents Drafting, Mechanizing, and Generalizing from Human Hints

    Apr 17, 2026Kevin Kappelmann, Maximilian Schäffeler, Lukas Stevens +3Interactive Theorem ProvingAutoformalization

  24. Munkres' General Topology Autoformalized in Isabelle/HOL

    Apr 8, 2026Dustin Bryant, Jonathan Julián Huerta y Munive, Cezary Kaliszyk +1AutoformalizationInteractive Theorem Proving

  25. Explorable Proofs: Making Written Proofs Explorable by Grounding Them in Formal Representations

    Apr 3, 2026Hita Kambhamettu, Will Crichton, Sean Welleck +2LLM GroundingInteractive Theorem Proving

  26. WybeCoder: Verified Imperative Code Generation

    Mar 31, 2026Fabian Gloeckle, Mantas Baksys, Darius Feher +5Verified Code GenerationFormal Verification

  27. Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP

    Mar 20, 2026Guillaume Baudart, Marc Lelarge, Tristan Stérin +1Large Language Model-Guided Theorem ProvingAutomated Theorem Proving