Bilevel Optimization of Agent Skills via Monte Carlo Tree Search

ArXi:2604.15709v1 Announce Type: new Agent \texttt{skills} are structured collections of instructions, tools, and ing resources that help large language model (LLM) agents perform particular classes of tasks. Empirical evidence shows that the design of \texttt{skills} can materially affect agent task performance, yet systematically optimizing \texttt{skills} remains challenging. Since a \texttt{skill} comprises instructions, tools, and ing resources in a structured way, optimizing it requires jointly determining both the structure of these components and the content each component contains.