4 papers
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents
Qianhan Feng, Zhongzhen Huang, Yakun Zhu +2
As agents continuously improve by generating and revising Skills, the process that discovers and refines those Skills becomes a learnable object in its own right. Task-Skills direc…
MedExpMem: Adapting Experience Memory for Differential Diagnosis
Qianhan Feng, Zhongzhen Huang, Yakun Zhu +4
Experienced physicians develop diagnostic expertise through clinical practice, acquiring not only disease knowledge but also the ability to differentiate confusable conditions. Cur…
CP-Env: Evaluating Large Language Models on Clinical Pathways in a Controllable Hospital Environment
Yakun Zhu, Zhongzhen Huang, Qianhan Feng +5
Medical care follows complex clinical pathways that extend beyond isolated physician-patient encounters, emphasizing decision-making and transitions between different stages. Curre…
UCAgents: Unidirectional Convergence for Visual Evidence Anchored Multi-Agent Medical Decision-Making
Qianhan Feng, Zhongzhen Huang, Yakun Zhu +2
Vision-Language Models (VLMs) show promise in medical diagnosis, yet suffer from reasoning detachment, where linguistically fluent explanations drift from verifiable image evidence…