paper-with-me

홈 › Papers

Clinical Harness for Governable Medical AI Skill Ecosystems

2026-06-25 · Tianhan Xu, Lei Bao, Zhe Hu, Tian Shen, Yongxiang Wang arxiv

Medical AI remains organized around isolated models, whereas care requires accountable capabilities that persist across time. We define clinical AI skills and propose the Clinical Harness, a runtime governance architecture that registers, orchestrates, constrains and monitors them. Using osteoporosis as an exemplar, we show how knowledge-driven, data-driven and physics-enhanced skills can support lifecycle care and provide a governed substrate for future medical agents.

📄 PDF Abstract BibTeX arXiv:2606.26494

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Harnessing AtomisticSkills for Agentic Atomistic Research

2026-05-18 · Bowen Deng, Bohan Li, Matthew Cox, Hoje Chun 외 arxiv

Computational materials science and chemistry span vast knowledge domains and fractured software ecosystems. Although large language models (LLMs) have demonstrated research capabilities, scaling monolithic agents to man…

Drug Discovery

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

2026-05-30 · Su Wang, Pin Qian, Yihang Chen, Junxian You 외 arxiv

LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set. We study a core safety problem in agentic AI systems: whether individually safe skills can compose into unsa…

Leveraging Large Language Model as Simulated Patients for Clinical Education

2024-04-13 · Yanzeng Li, Cheng Zeng, Jialun Zhong, Ruoyu Zhang 외

Simulated Patients (SPs) play a crucial role in clinical medical education by providing realistic scenarios for student practice. However, the high cost of training and hiring qualified SPs, along with the heavy workload…

DiagnosticLanguage ModelingLanguage ModellingLarge Language Model

TARSE: Test-Time Adaptation via Retrieval of Skills and Experience for Reasoning Agents

2026-03-01 · Junda Wang, Zonghai Tao, Hansi Zeng, Zhichao Yang 외 arxiv

Complex clinical decision making often fails not because a model lacks facts, but because it cannot reliably select and apply the right procedural knowledge and the right prior example at the right reasoning step. We fra…

Test-time AdaptationQuestion AnsweringDecision Making

SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents

2026-06-15 · Qiao Xiao, Haochen Shi, Yisen Gao, Wenbin Hu 외 arxiv

Large language model (LLM) agents increasingly rely on agent harnesses that manage context, tools, and multi-turn execution, making tools a central interface for acting in realistic digital environments. As harness-conne…