SOURCE-LINKED INTELLIGENCE

DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to distill these traces into reusable feedback without post-hoc outcome labels, drawing on their evidence of local progress, recovery, and unfinished requirements. We introduce DENSE (Distilling Evidence from Nested Subtask Executions), which organizes this evidence into evidence-grounded nested shortcut trees. DENSE compresses redundant attempts, reconciles issues across levels using recovery evidence, and summarizes completed branches while expa

Read original source ↗ Open in workspace

recordType

paper

region

Global