Recent advancements in large language models (LLMs) have brought significant changes to various dimains, especially through LLM-driven autonomous agents. These agents are now capable of collaborating seamlessly, splitting tasks and enhancing accuracy, thus minimizing the need for human involvement. However, these agents often approach a diverse range of tasks in isolation, without benefiting from past experiences. This isolation can lead to repeated mistakes and inefficient trials in task solving. To this end, this paper introduces Experiential Co-Learning, a novel framework in which instructor and assistant agents gather shortcut-oriented experiences from their historical trajectories and use these past experiences for mutual reasoning. This paradigm, enriched with previous experiences, equips agents to more effectively address unseen tasks.

翻译：近期大型语言模型的进步为各个领域带来了显著变革，尤其体现在由大型语言模型驱动的自主智能体方面。这些智能体如今能够无缝协作，拆分任务并提升准确性，从而减少对人工介入的需求。然而，这些智能体在处理各种任务时往往彼此孤立，未能从过往经验中获益。这种孤立性可能导致任务求解过程中重复出现错误和低效尝试。为此，本文提出经验协同学习这一新型框架，其中指导型智能体与助手型智能体从其历史轨迹中收集捷径导向经验，并利用这些过往经验进行相互推理。这种富含既往经验的范式使智能体能够更有效地应对未见过的新任务。