Copertina

An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Gelei, Tang, Ningzhi, Li, Xueyang, Li, Toby Jia-Jun, Zheng, Zhi, Jin, Wei, Shi, Yiyu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
di: Tang, Ningzhi, et al.
Pubblicazione: (2026)

AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rays
di: Li, Xueyang, et al.
Pubblicazione: (2025)

Enabling On-Device Learning via Experience Replay with Efficient Dataset Condensation
di: Xu, Gelei, et al.
Pubblicazione: (2024)

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
di: Liu, Yi, et al.
Pubblicazione: (2026)

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
di: Chen, Zhihao, et al.
Pubblicazione: (2026)

The Cost of Local and Global Fairness in Federated Learning
di: Duan, Yuying, et al.
Pubblicazione: (2025)

NaturalEdit: Code Modification through Direct Interaction with Adaptive Natural Language Representation
di: Tang, Ningzhi, et al.
Pubblicazione: (2025)

An Empirical Study of Agent Developer Practices in AI Agent Frameworks
di: Wang, Yanlin, et al.
Pubblicazione: (2025)

H-CNN-ViT: A Hierarchical Gated Attention Multi-Branch Model for Bladder Cancer Recurrence Prediction
di: Li, Xueyang, et al.
Pubblicazione: (2025)

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
di: Liu, Hongyi, et al.
Pubblicazione: (2026)

"Are You Sure?": An Empirical Study of Human Perception Vulnerability in LLM-Driven Agentic Systems
di: Li, Xinfeng, et al.
Pubblicazione: (2026)

Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
di: Liu, Yi, et al.
Pubblicazione: (2023)

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills
di: Liu, Yi, et al.
Pubblicazione: (2026)

Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study
di: Zhang, Li, et al.
Pubblicazione: (2025)

Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions
di: Tang, Ningzhi, et al.
Pubblicazione: (2026)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
di: Qu, Yubin, et al.
Pubblicazione: (2026)

In-Context Defense in Computer Agents: An Empirical Study
di: Yang, Pei, et al.
Pubblicazione: (2025)

ALLOY: Generating Reusable Agent Workflows from User Demonstration
di: Li, Jiawen, et al.
Pubblicazione: (2025)

EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation
di: Zhang, Aimin, et al.
Pubblicazione: (2026)

A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
di: Xu, Zihao, et al.
Pubblicazione: (2024)

SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
di: Xu, Duling, et al.
Pubblicazione: (2026)

CUA-Skill: Develop Skills for Computer Using Agent
di: Chen, Tianyi, et al.
Pubblicazione: (2026)

An Empirical Study of Multi-Agent Collaboration for Automated Research
di: Shen, Yang, et al.
Pubblicazione: (2026)

OAgents: An Empirical Study of Building Effective Agents
di: Zhu, He, et al.
Pubblicazione: (2025)

SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
di: Yang, Min, et al.
Pubblicazione: (2026)

From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?
di: Xu, Binyan, et al.
Pubblicazione: (2026)

Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client
di: Xia, Jun, et al.
Pubblicazione: (2024)

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
di: Zhang, Hanrong, et al.
Pubblicazione: (2026)

Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices
di: Qin, Ruiyang, et al.
Pubblicazione: (2024)

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
di: Zhou, Yifan, et al.
Pubblicazione: (2026)

Odyssey: Empowering Minecraft Agents with Open-World Skills
di: Liu, Shunyu, et al.
Pubblicazione: (2024)

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
di: Huang, Zisu, et al.
Pubblicazione: (2026)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
di: Feng, Yunhao, et al.
Pubblicazione: (2026)

SkillsInjector: Dynamic Skill Context Construction for LLM Agents
di: Li, Yanchao, et al.
Pubblicazione: (2026)

An Empirical Study of Proactive Coding Assistants in Real-World Software Development
di: Li, Lehui, et al.
Pubblicazione: (2026)

ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
di: Lu, Zijian, et al.
Pubblicazione: (2026)

EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
di: Ju, Ruofei, et al.
Pubblicazione: (2026)

Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
di: Mi, Qirui, et al.
Pubblicazione: (2026)

CoCo Matrix: Taxonomy of Cognitive Contributions in Co-writing with Intelligent Agents
di: Wan, Ruyuan, et al.
Pubblicazione: (2024)

Key Considerations for Domain Expert Involvement in LLM Design and Evaluation: An Ethnographic Study
di: Szymanski, Annalisa, et al.
Pubblicazione: (2026)