Evidence Over Plans: Online Trajectory Verification for Skill Distillation 事件

Evidence Over Plans: Online Trajectory Verification for Skill Distillation arXiv:2605.09192v2 Announce Type: replace Abstract: Agent skills can remarkably improve task success rates by using human-written procedural documents, but their quality is difficult to assess without environment-grounded verification. Existing skill generation methods heavily rely on preference logs rather than direct environment interaction, often yielding negligible or even degraded gains. We identify that it is a fun