Verified70% confidenceFactExact time
DeepMind's AlphaProof combined large language models with Lean 4 in 2024 and used reinforcement learning to self-play in a formal environment to generate and verify proof steps.
4
Sources
70%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
Can AI Prove Mathematical Conjectures? The Truth Behind the GPT-5.6 Incident and the Limits of Large Language Models
hackernewshackernews7/10/2026
Related Claims
UnverifiedDeepMind的AlphaProof直接在Lean4环境中进行强化学习84% similarUnverifiedAfter 2022, DeepMind's AlphaProof and various large language models began combining neural networks with symbolic reasoning.84% similarVerifiedGoogle DeepMind's AlphaProof combines a large language model with the formal proof verifier Lean, adopting a 'generation-verification' closed-loop mechanism.77% similarUnverifiedProjects such as DeepMind's AlphaProof and Meta's COPRA are exploring the use of large language models to automatically generate Lean proof scripts, which are then verified by Lean.77% similarVerifiedDeepMind's AlphaProof and AlphaGeometry systems adopt a step-by-step verification approach.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/487641API
curl https://kongchang.com/api/v1/knowledge/claims/487641MCP
get_claim(id=487641)