מעקב אחר גבולות ניידים

תקציר מקורי באנגליתarXiv:2609.06671v1 Announce Type: new Abstract: Group-based RLVR methods estimate advantages by repeatedly sampling multiple trajectories for each prompt, making long-horizon agent training expensive and discarding useful experience accumulated across iterations. We ask whether historical experience can replace these repeated within-iteration comparisons without directly optimizing on stale trajectories. We introduce Long-Short Term Advantage Estimator (LSTAE), a single-stream RL algorithm that uses history for advantage estimation while updating the policy only with the current rollout. LSTAE maintains a persistent tracker for each task anchor. At the trajectory level (long term), a drift-aware historical baseline tracks the anchor's moving success frontier and measures the relative contr