AI RESEARCH
When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills
arXiv CS.AI
•
ArXi:2605.25832v1 Announce Type: cross Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape the next population but are not preserved as reusable design knowledge. We present Auto-Robotist, a self-evolving LLM agent that distills morphology-search traces into an explicit natural-language skill library.