From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents
This work presents an online skill-evolution framework that converts interaction trajectories and evaluator feedback into a persistent, versioned library of reusable procedures and characterize evolving skill libraries as auditable, shared procedural memory that can improve a fixed computer-use stack.
Long-Tao Hu, Xiao Liang, Lin-Chao Zhu
· 1 citation