5 papers
POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents
Qiaoyuan Zheng, Yiqu Yang, Qi Gao +1
LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what may and must not be shared, a…
Evolving Interactive Diagnostic Agents in a Virtual Clinical Environment
Pengcheng Qiu, Chaoyi Wu, Junwei Liu +11
We present a framework for training large language models (LLMs) as diagnostic agents with reinforcement learning, enabling them to manage multi-turn interactive diagnostic process…
End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning
Qiaoyu Zheng, Yuze Sun, Chaoyi Wu +8
The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While…
How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?
Qiaoyu Zheng, Chaoyi Wu, Pengcheng Qiu +4
We introduce RadA-BenchPlat, an evaluation platform that benchmarks the performance of large language models (LLMs) act as agent cores in radiology environments using 2,200 radiolo…
M^3Builder: A Multi-Agent System for Automated Machine Learning in Medical Imaging
Jinghao Feng, Qiaoyu Zheng, Chaoyi Wu +4
Agentic AI systems have gained significant attention for their ability to autonomously perform complex tasks. However, their reliance on well-prepared tools limits their applicabil…