Skip to main content
Search

Yuxin Xiao

1 related articles

Subscribe to updates
  1. arXiv

    Agents learn online without only reading forward: revising retrieved reflections from trajectories beats memory and prompt optimization on three benchmarks

    Agents running over long interaction streams must adapt online to distribution shifts, yet existing agent harnesses either evolve their state through forward information flow alone or rely on extra replay or validation data for optimization. ReHarness combines forward read and write with backward revision under a strictly online streaming protocol: after each instance, the resulting trajectory becomes feedback that revises the reflections retrieved for that instance, propagating feedback backward through the textual harness state. Across three continual learning benchmarks and three language model backbones, it consistently outperforms raw-context baselines, memory- and reflection-based methods, and prompt optimization approaches.

You’re all caught up