AI RESEARCH
From AI Assistant to AI Scientist: Autonomous Discovery of LLM-RL Algorithms with LLM Agents
arXiv CS.CL
•
ArXi:2603.23951v1 Announce Type: new Discovering improved policy optimization algorithms for language models remains a costly manual process requiring repeated mechanism-level modification and validation. Unlike simple combinatorial code search, this problem requires searching over algorithmic mechanisms tightly coupled with