Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization
Self-evolving agents can continually improve their behavior, while tools define the executable action space through which they interact with the environment. However, exposing the full tool library to model introduces substantial irrelevant context and can impair tool-use decisions. We study tool-space self-evolution,...
Xuanqi Zhang, Rui-Nan Jin, Run Yang et al.
· 0 citations