Turing AgentAgentic Formal Verification for Mathematical Research

Our vision

  • Fast

    Verify at AI speed.

  • Faithful

    Prove the claim as stated.

  • For TCS

    Formal foundations for TCS.

FRONTIER RESEARCH BREAKTHROUGH OCTOBER 2026

OpenAI’s Unfinished Lean Proofs, Completed by Turing Agent

Explore All 3 Problems

In October 2026, OpenAI released 722 mathematical manuscripts authored by frontier models. Of 121 theoretical computer science problems, 22 formalizations remained unfinished. Highlighted here are 3 of these problems with Lean-kernel-checked proofs.

Architecture

How the harness works

Full harness design & details →
01

Fix a faithful statement

A theorem-formalization agent writes the Lean statement from Mathlib and CSLib definitions, then reviews domains, quantifiers and assumptions against the source. Once checks pass, the statement is locked.

02

Grow a proof DAG in parallel

Proof agents split goals into claims only after Lean confirms the children imply the parent, prove independent branches concurrently, and keep an experience pool of what worked and what failed.

03

Verify independently

An independent Lean kernel rechecks the assembled proof with an axiom audit, and a review agent checks that the proof still follows the original argument.

Updates

What's new

All news →
    Reference

    Citation

    If you use Turing Agent or the results on this page, please cite:

    @techreport{turingagent2026,
      title       = {Turing Agent: Agentic Formal Verification
                     for Mathematical Research},
      author      = {{Turing Agent Team}},
      institution = {Shanghai Artificial Intelligence Laboratory},
      year        = {2026}
    }