Adaptive Reasoning and Acting in Medical Language Agents

Abhishek Dutta, Yen-Che Hsiao

Keywords: llm agents, medical llm

TL;DR: This paper presents an innovative large language model (LLM) agent framework for enhancing diagnostic accuracy in simulated clinical environments.

Abstract: This paper presents an innovative large language model (LLM) agent framework for enhancing diagnostic accuracy in simulated clinical environments using the AgentClinic benchmark. The proposed automatic correction enables doctor agents to iteratively refine their reasoning and actions following incorrect diagnoses, fostering improved decision-making over time. Experiments show that the implementation of the adaptive LLM-based doctor agents achieve correct diagnoses through dynamic interactions with simulated patients. The evaluations highlight the capacity of autonomous agents to adapt and improve in complex medical scenarios. Future enhancements will focus on refining the algorithm and expanding its applicability across a wider range of tasks and different large language models.

Submission Number: 91