AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Computer-use agents can execute increasingly complex tasks in graphical interfaces, but their interaction experience is typically transient: procedural knowledge acquired from one rollout is not systematically retained, refined, and reused in later tasks. Existing skill libraries provide external procedural knowledge, yet their incremental value over the same agent operating without skills, as well as their longitudinal dynamics under repeated interaction, remain insufficiently characterized. We present an online skill-evolution framework that converts interaction trajectories and evaluator fe

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T22:31:48.298Z. This is not the publication date.