Evidence Over Plans: Online Trajectory Verification for Skill Distillation
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 fundamental timing bottleneck: robust skills should be posterior-based, distilled from empirical environment interaction rather than prior plans. In this study, we introduce the Posterior Distillation Index (PDI), a trajectory-level metric that quantifies how well a distilled skill is grounded in the task-environment evidence....
| Authors | Yang Zhou, Zihan Dong, Zhenting Wang et al. |
|---|---|
| Primary category | cs.AI |
| Published | 9 May 2026 |
| Last updated at source | 3 June 2026 |
Connected in the knowledge graph
- EtaYang10th/SPARK_PDI_TrajectoryDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.