LLMs Can Simulate Standardized Patients via Agent Coevolution
Training medical personnel using standardized patients (SPs) remains a complex challenge, requiring extensive domain expertise and role-specific practice. Previous research on Large Language Model (LLM)-based SPs mostly focuses on improving data retrieval accuracy or adjusting prompts through human feedback. However, this focus has overlooked the critical need for patient agents to learn a standardized presentation pattern that transforms data into human-like patient responses through unsupervised simulations. To address this gap, we propose EvoPatient, a novel simulated patient framework in which a patient agent and doctor agents simulate the diagnostic process through multi-turn dialogues, simultaneously gathering experience to improve the quality of both questions and answers, ultimately enabling human doctor training. Extensive experiments on various cases demonstrate that, by providing only overall SP requirements, our framework improves over existing reasoning methods by more than 10\% in requirement alignment and better human preference, while achieving an optimal balance of resource consumption after evolving over 200 cases for 10 hours, with excellent generalizability. Our system will be available at https://github.com/ZJUMAI/EvoPatient.
Code (1)
Tasks
DiagnosticLanguage ModelingLanguage ModellingLarge Language ModelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PSYCHE: A Multi-faceted Patient Simulation Framework for Evaluation of Psychiatric Assessment Conversational Agents
Recent advances in large language models (LLMs) have accelerated the development of conversational agents capable of generating human-like responses. Since psychiatric assessments typically involve complex conversational…
BenchmarkingDiscovering Novel LLM Experts via Task-Capability Coevolution
Frontier model developers aim to train models continually to possess emergent, diverse capabilities. To extend capabilities, the current pre-training and post-training paradigm requires manually starting training runs wi…
Synthetic Data GenerationA coevolutionary approach to deep multi-agent reinforcement learning
Traditionally, Deep Artificial Neural Networks (DNN's) are trained through gradient descent. Recent research shows that Deep Neuroevolution (DNE) is also capable of evolving multi-million-parameter DNN's, which proved to…
Atari GamesDecision MakingMulti-agent Reinforcement Learningreinforcement-learning+2Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. However, prevailing RL fine-tuning methods predominantly rely on PPO and its variants. Though…
GSM8KMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1Human or LLM as Standardized Patients? A Comparative Study for Medical Education
Standardized patients (SPs) are indispensable for clinical skills training but remain expensive and difficult to scale. Although large language model (LLM)-based virtual standardized patients (VSPs) have been proposed as…
Response Generation