AI RESEARCH

POLCA: Stochastic Generative Optimization with LLM

arXiv CS.AI

ArXi:2603.14769v1 Announce Type: cross Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic generative optimization problem where a generative language model acts as the optimizer, guided by numerical rewards and text feedback to discover the best system. We