Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than merely responding to queries from human users. Most existing language agents, however, are not optimized using environment-specific rewards. Although some agents enable iterative refinement through verbal feedback, they do not reason and plan in ways that are compatible with gradient-based learning from rewards. This paper introduces a principled framework for reinforcing large language agents by learning a retrospective model, which automatically tunes the language agent prompts from environment feedback through policy gradient. Specifically, our proposed agent architecture learns from rewards across multiple environments and tasks, for fine-tuning a pre-trained language model which refines the language agent prompt by summarizing the root cause of prior failed attempts and proposing action plans. Experimental results on various tasks demonstrate that the language agents improve over time and that our approach considerably outperforms baselines that do not properly leverage gradients from the environment. This demonstrates that using policy gradient optimization to improve language agents, for which we believe our work is one of the first, seems promising and can be applied to optimize other models in the agent architecture to enhance agent performances over time.

翻译：近几个月出现了一股强大的新趋势，即大型语言模型被增强为自主语言智能体，能够独立执行面向目标的多步骤任务，而不仅仅是回应用户的查询。然而，现有的大多数语言智能体并未利用环境特定的奖励进行优化。尽管部分智能体通过语言反馈实现了迭代改进，但它们无法以兼容基于梯度的奖励学习方式进行推理和规划。本文提出了一种通过反思模型强化大型语言智能体的原则性框架——该框架通过策略梯度自动根据环境反馈调整语言智能体的提示词。具体而言，我们提出的智能体架构可跨多个环境和任务学习奖励，通过微调预训练语言模型来总结先前失败案例的根本原因并提出行动计划，从而优化语言智能体的提示词。在多项任务上的实验结果表明，语言智能体的性能随时间持续提升，且我们的方法显著优于未充分利用环境梯度的基线模型。这表明，使用策略梯度优化来改进语言智能体（我们认为本文是该领域的先驱工作之一）具有广阔前景，并可应用于优化智能体架构中的其他模型，以持续增强智能体性能。