DeepMind details AlphaProof Nexus: LLM proof agents now proving research-level math
pushmeet · x · 2026-10-09
Google DeepMind's Pushmeet Kohli outlines its proof-agent stack: from AlphaProof's IMO silver medal in 2024 to LLM-powered AlphaProof Nexus agents, which collaborator Gergely Bérczi of Aarhus University has used to prove research-level results. The technical paper appears in Science.
More from Research
- Test-Time Structure-Space Search lifts antibody design success from 16% to 78% — anshulkundaje · 2026-10-09
- aimotive driving dataset: train labels come from a tracker that sees the future — RexDouglass · 2026-10-09
- Yale-led study finds symbolic structure inside LLM representations — tallinzen · 2026-10-09
- Discrete Diffusion Meetup at COLM: Oct 8, Grand Ballroom — yuntiandeng · 2026-10-09
- Astra 机器人控制实测:Johns Hopkins 深度评测其运动与控制理解 — jmin__cho · 2026-10-09
- Tavily's 93% live-retrieval agent study challenged: prompts were domain-anchored — edwin · 2026-10-09