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

TL;DR

This paper introduces 'Introspective Tips', a prompt-based method enabling large language models to self-improve decision-making in various scenarios without fine-tuning, demonstrated through extensive game experiments.

Contribution

The paper presents a novel prompt-based approach allowing LLMs to self-optimize decision policies across multiple scenarios without parameter fine-tuning.

Findings

Enhanced performance in few-shot and zero-shot settings

Effective self-improvement through introspective tips

Superior results across over 100 TextWorld games

Abstract

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.