內省提示：用於上下文決策的大型語言模型

摘要

大型語言模型（LLMs）的出現顯著影響了自然語言處理，在各種任務中展現出優異的結果。在這項研究中，我們利用“內省提示”來幫助LLMs自我優化其決策過程。通過內省地檢視軌跡，LLM通過生成簡潔而有價值的提示來完善其策略。我們的方法通過考慮三個基本情境來提高代理人在少樣本和零樣本學習情況下的表現：從代理人過去的經驗中學習、整合專家示範以及在不同遊戲間進行泛化。重要的是，我們實現了這些改進，而無需微調LLM參數；相反，我們調整提示以從上述三種情況中獲得見解的泛化。我們的框架不僅支持，而且強調了在上下文決策中使用LLM的優勢。在TextWorld中涉及超過100個遊戲的實驗說明了我們方法的優越性能。

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.

內省提示：用於上下文決策的大型語言模型

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

摘要

Support