Concept · 7 episode(s)

Formal Theorem Proving

← all concepts

Definition

Formal Theorem Proving is the practice of constructing mathematical proofs in a machine-readable language such that a proof assistant or compiler can mechanically verify every logical step is valid. Unlike informal proofs reviewed by human mathematicians, this approach provides a hard correctness guarantee — a proof that compiles in a system like Lean is, by construction, free of gaps or logical errors that a reviewer might overlook.

Episodes covering this

  1. 273
    When 85% on SWE-bench Turns Into 58% Under Proof
    SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?
    Ma, Mikek, Li et al. · UCBerkeley·15 min·Sep 21, 2026
  2. 271
    The Proof Counter Hit Zero While a Third of It Was Missing
    Long-horizon autoformalization of a core theorem underlying MIP* = RE
    Lu, Deng, Zhu et al. · Max-Planck-Institut für Quantenoptik·17 min·Sep 19, 2026
  3. 260
    One Line of Lean Faked 34 Proofs, and 99 Agents Copied It
    A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
    Paglieri, Cross, Genewein et al. · Google DeepMind·25 min·Sep 05, 2026
  4. 188
    A Coding Agent Found a Hole in a Peer-Reviewed STOC Proof for Five Dollars
    Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics
    Moakhar, Gholami, Springer et al. · University of Maryland·20 min·Jul 02, 2026
  5. 133
    How MiniMax Turned a Reward-Hacking Disaster Into Olympiad Gold
    MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
    Chen, Zhang, Zhang et al. · MiniMax / The Chinese University of Hong Kong·34 min·Jun 12, 2026
  6. 122
    When Your Coding Agent Lies About the Fix: Verifying the Plan Before the Model Runs
    Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
    Wang, Huang, Wang et al. · University of Illinois Urbana-Champaign·24 min·Jun 09, 2026
  7. 117
    How an Open AI System Verified 672 Hard Math Proofs for Under $300
    Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
    Chung, Cai, Li et al. · Princeton University·26 min·Jun 05, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.