error-driven-refinement

Tag

Cards List
#error-driven-refinement

Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents

arXiv cs.AI · 2026-06-10 Cached

Trace2Policy extracts human-readable decision rules from expert behavior traces and iteratively refines them via error-driven skill refinement, outperforming pure LLM baselines on compliance-sensitive tasks in logistics.

0 favorites 0 likes
← Back to home

Submit Feedback