Robust Soft Skill Adaptation via Behavioral Localization in Tool-Using Agents
Text skills can extend the capabilities of tool-using agents, but long skill descriptions increase computational costs. Soft prompts provide a compact alternative, yet learning from entire successful trajectories may also introduce unnecessary behavioral changes. We find that the useful effect of a text skill is highly concentrated in a small subset of trajectory positions. Based on this…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
