AutoOPT discovers new optimization algorithms, introducing the lemniscate constant

ErnestRyu · x · 2026-08-19

Optimization researcher Ernest Ryu presents two new algorithms found by the LLM-driven AutoOPT system: the Lemniscate Accelerated Gradient Method and Analytic ITEM-f.

Both contain novel components in their construction and convergence proofs; Ryu says it's the first time he has seen the lemniscate constant arise in optimization.

He frames this as a disruptive change for optimization researchers — the craftsmanship of designing efficient algorithms and proving convergence guarantees, a skill he spent years refining, will be 90% automated. But it's also an opportunity: researchers should embrace these tools to accelerate research and tackle harder problems.

Related event: LLM-Driven AutoOPT Discovers New Optimization Algorithms(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →