Query-conditioned reuse beats replaying whole trajectories: +10.7 points success on 2,391 tasks with 48.9% fewer online tokens

arXiv·medium signalXBlueskyLinkedInCopy link

This paper (arXiv 2608.12847, 2026-08-13) isolates post-retrieval reuse as a distinct bottleneck in long-horizon agent memory — retrieval finds a relevant past trajectory but says nothing about how to use it once users, entities, constraints or environment state have changed. Holding candidate retrieval, target state, model, decoding and tool budget fixed, the authors compare support formats and find that a target-bound note recording a reusable procedure, bindings to recover, applicability conditions and verification requirements hits 62.3% average success across WebArena, WorkArena and AppWorld — 10.7 points above injecting the full trajectory — while spending 48.9% fewer online tokens. Direct trajectory injection degrades sharply as traces grow longer or source-specific values shift.