AutoOPT: Automating Optimization Research with GPT-5.6 Sol
ErnestRyu · x · 2026-08-19
Researchers presented AutoOPT, a domain-specific harness for end-to-end automation of optimization research using LLMs like GPT-5.6 Sol. The framework organizes discovery into four stages: numerical design via BnB-PEP, symbolic discovery of analytic descriptions and proofs via LLMs, formal verification in Lean 4, and human interpretation. Two case studies were demonstrated: a new 'lemniscate acceleration' method and the analytic description of ITEM-f.
More from Research
- MIT PhD Sharut Gupta joins DeepMind; Isola hails her representational alignment defense talk — phillip_isola · 2026-10-16
- 36 primitives, just 10 parameters each: a remarkably precise T-pose body fit — letandrewcook · 2026-10-16
- Interp researcher pushes back: if you can't simulate a neuron, you haven't explained it — nabla_theta · 2026-10-16
- MLP-Splatting (ECCV 2026) code released: MLPs as light-field primitives instead of Gaussians — AjdDavison · 2026-10-16
- Four-page solution to subcubic APSP builds intuition for Anthropic-AI-aided breakthrough — gautamcgoel · 2026-10-16
- ATAS: Zhejiang-led team builds world-state memory framework for consistent agentic video generation — CSProfKGD · 2026-10-16