Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
This addresses the problem of error correction in LLMs for researchers and practitioners, but it is incremental as it builds on existing self-reflection concepts.
The study tackled the problem of improving problem-solving performance in large language models (LLMs) by implementing self-reflection, and the result showed that LLM agents significantly enhanced their performance with a p-value < 0.001.
In this study, we investigated the effects of self-reflection in large language models (LLMs) on problem-solving performance. We instructed nine popular LLMs to answer a series of multiple-choice questions to provide a performance baseline. For each incorrectly answered question, we instructed eight types of self-reflecting LLM agents to reflect on their mistakes and provide themselves with guidance to improve problem-solving. Then, using this guidance, each self-reflecting agent attempted to re-answer the same questions. Our results indicate that LLM agents are able to significantly improve their problem-solving performance through self-reflection ($p < 0.001$). In addition, we compared the various types of self-reflection to determine their individual contribution to performance. All code and data are available on GitHub at https://github.com/matthewrenze/self-reflection