内省提示：用于上下文决策的大型语言模型

摘要

大型语言模型（LLMs）的出现显著影响了自然语言处理，在各种任务中展示出卓越的结果。在这项研究中，我们采用“内省提示”来帮助LLMs自我优化决策。通过内省地检查轨迹，LLM通过生成简洁而有价值的提示来完善其策略。我们的方法通过考虑三种重要情景来增强代理的性能，即从代理的过去经验中学习，整合专家演示，以及在不同游戏中进行泛化。重要的是，我们实现这些改进而无需微调LLM参数；相反，我们调整提示以从上述三种情况中泛化见解。我们的框架不仅支持而且强调了在上下文决策中使用LLM的优势。在TextWorld中涉及超过100个游戏的实验展示了我们方法的卓越性能。

English

The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in self-optimizing their decision-making. By introspectively examining trajectories, LLM refines its policy by generating succinct and valuable tips. Our method enhances the agent's performance in both few-shot and zero-shot learning situations by considering three essential scenarios: learning from the agent's past experiences, integrating expert demonstrations, and generalizing across diverse games. Importantly, we accomplish these improvements without fine-tuning the LLM parameters; rather, we adjust the prompt to generalize insights from the three aforementioned situations. Our framework not only supports but also emphasizes the advantage of employing LLM in in-contxt decision-making. Experiments involving over 100 games in TextWorld illustrate the superior performance of our approach.

内省提示：用于上下文决策的大型语言模型

Introspective Tips: Large Language Model for In-Context Decision Making

摘要

Support