DENSE: ניפוץ נתיבי סולם קצרים לצורך עדכון עצמי

תקציר מקורי באנגליתarXiv:2609.21423v5 Announce Type: replace Abstract: Online agent deployments accumulate execution trajectories at massive scale and behavioral diversity, for which predefined annotation criteria hardly exist. Extracting useful evidence therefore demands costly manual annotation or verifier signals that fail to scale, leaving valuable evidence buried among redundant, incomplete, and failed executions. This raises a question: without post-execution rewards or correctness labels, how can reusable experience be distilled from the trajectories themselves? To address this challenge, we introduce DENSE (Distilling Evidence from Nested Subtask Executions), which organizes trajectory-derived evidence into nested shortcut trees. By consolidating redundant attempts, identifying resolved subtasks, and