Back to Home
arXiv AI··Papers & Tech

Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons

中文摘要

智能体通过“自主修正”机制从错误中学习,实现持续改进,解决了传统方法中上下文易遗忘或微调成本高的问题。

English Summary

Self-Direction enables agents to learn from mistakes through autonomous repair, ensuring continuous improvement while overcoming limitations of temporary in-context reflection and expensive fine-tuning.

Original Excerpt

arXiv:2610.31846v1 Announce Type: new Abstract: Intelligent agents should learn from their mistakes so that experience leads to continuous improvement. Yet today's agents recover from a mistake only temporarily: in-context reflections are easily forgotten across sessions and compete for limited context, while full-parameter fine-tuning is expensive and can interfere with existing capabilities. We introduce Self-Direction, a mechanism for agents to learn from mistakes that combines the benefits of temporary in-context retries and policy updates. When an agent fails a task, it reflects on its own trajectory in order to extract a lesson and immediately distills it into a lightweight low-rank adapter. By keeping the original weights frozen, Self-Direction prevents adapter training from overwriting base-model parameters while training additional parameters equivalent to ~0.02% of the base model's parameter count for each adapter. The agent then saves these adapters in a persistent library of lessons, automatically routing them to solve related problems later. Experiments with agents based on open-weight models from the Qwen family across open-ended research (GAIA), tool-use workflows (C…