Berkeley team packages LLM optimizer methods into GEPA, then beats them with omni

mrdrozdov · x · 2026-07-24

Researchers at Berkeley’s STAR Lab are packaging multiple LLM-based optimization algorithms into a single API via GEPA, and a new meta-optimizer, optimizeanything omni, combines them to exploit complementary strengths.

Related event: Berkeley Team Releases 'omni', a Meta-Optimizer for LLMs(3 posts)→

Original post →

More from coding & agent

coding & agent channel →