[KongchangAI]
ProductTuring Agent框架

Turing Agent

An end-to-end formal verification agent framework for research-level mathematical problems that adopts a dual-scale architecture integrating theorem formalization and proof formalization agents, combined with mechanisms such as structured proof decomposition, parallel verification, and selective semantic review.

Timeline (last 90 days)

Nov 17

Turing Agent is an agent framework designed to orchestrate end-to-end formal verification, specifically targeting research-level mathematical problems.

Unverified50%
Nov 17

Turing Agent achieved a faithful formalization success rate of about 57-62% on Formal TCS Bench.

Unverified50%
Nov 17

Turing Agent achieved an overall pass@1 score of 83% on the TCS-focused RLMEval subset.

Unverified50%
Nov 17

Turing Agent's tests used models such as GLM-5.3 and DeepSeek-V4-Pro.

Unverified50%
Nov 17

Turing Agent, built on DeepSeek, successfully completed the formal verification of three previously unsolved TCS tasks from OpenAI's October 2026 collection.

Unverified50%
Nov 17

One particularly difficult TCS problem required about one hundred formally verified auxiliary statements to complete.

Unverified50%

All Facts (6)

Source Articles