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.

Related event: AutoOPT: Automating Optimization Research with GPT-5.6(2 posts)→

Original post →

More from Research

Research channel →