RESEARCH · RESEARCH · #1865
DeepMind's AlphaProof Nexus (using Gemini 3.1 Pro) solved dozens of open math problems, Science paper
A DeepMind system called AlphaProof Nexus, built around Gemini 3.1 Pro and using the Lean proof assistant (and optionally the specialized AlphaProof tool), produced formal proofs that the authors report solved dozens of open problems: nine of 353 open Erdős problems (two unsolved for 56 years), 44 conjectures from the OEIS, an open question in algebraic geometry, and an improved bound in min-max optimization; the team shared solutions online and published a peer-reviewed paper in Science. DeepMind says the nine Erdős solutions were found even without the AlphaProof specialist tool.
KEY POINTS
- A DeepMind system called AlphaProof Nexus, built around Gemini 3.1 Pro and using the Lean proof assistant (and optionally the specialized AlphaProof tool), produced formal proofs that the authors report solved dozens of open problems: nine of 353 open Erdős problems (two unsolved for 56 years), 44 conjectures from the OEIS, an open question in algebraic geometry, and an improved bound in min-max optimization; the team shared solutions online and published a peer-reviewed paper in Science.
- DeepMind says the nine Erdős solutions were found even without the AlphaProof specialist tool.
- This shows LLM-guided formal proof workflows can generate novel, peer-reviewed mathematical results and escalates debates over how AI-produced proofs should be validated and published.
WHY IT MATTERS
This shows LLM-guided formal proof workflows can generate novel, peer-reviewed mathematical results and escalates debates over how AI-produced proofs should be validated and published.