Adaptive Reasoning and Acting in Medical Language Agents

TL;DR

This paper introduces an adaptive LLM-based agent framework for medical diagnosis that iteratively refines reasoning and actions, leading to improved accuracy in simulated clinical environments.

Contribution

It presents a novel adaptive reasoning framework for medical language agents that enhances diagnostic accuracy through iterative correction and decision refinement.

Findings

Agents achieve correct diagnoses through dynamic interactions

Adaptive agents outperform static models in complex scenarios

The framework demonstrates significant improvement in simulated clinical tasks

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.