Saved in:
Bibliographic Details
Main Authors: Hou, Yingyong, Lao, Xinyuan, Wang, Huimei, Yao, Qianyu, Chen, Wei, Huang, Bocheng, Sun, Fei, Lv, Yuxian, Lei, Weiqi, Wen, Xueqian, Xia, Pengfei, Tan, Zhujun, Xie, Shengyang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.20441
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911614626693120
author Hou, Yingyong
Lao, Xinyuan
Wang, Huimei
Yao, Qianyu
Chen, Wei
Huang, Bocheng
Sun, Fei
Lv, Yuxian
Lei, Weiqi
Wen, Xueqian
Xia, Pengfei
Tan, Zhujun
Xie, Shengyang
author_facet Hou, Yingyong
Lao, Xinyuan
Wang, Huimei
Yao, Qianyu
Chen, Wei
Huang, Bocheng
Sun, Fei
Lv, Yuxian
Lei, Weiqi
Wen, Xueqian
Xia, Pengfei
Tan, Zhujun
Xie, Shengyang
contents Background: Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safeguards beyond general-purpose evaluation, including scientific integrity, methodological validity, reproducibility, and boundary safety. This study developed and preliminarily evaluated a domain-specific audit framework for medical research agent skills, with a focus on reliability against expert review. Methods: We developed MedSkillAudit (skill-auditor@1.0), a layered framework assessing skill release readiness before deployment. We evaluated 75 skills across five medical research categories (15 per category). Two experts independently assigned a quality score (0-100), an ordinal release disposition (Production Ready / Limited Release / Beta Only / Reject), and a high-risk failure flag. System-expert agreement was quantified using ICC(2,1) and linearly weighted Cohen's kappa, benchmarked against the human inter-rater baseline. Results: The mean consensus quality score was 72.4 (SD = 13.0); 57.3% of skills fell below the Limited Release threshold. MedSkillAudit achieved ICC(2,1) = 0.449 (95% CI: 0.250-0.610), exceeding the human inter-rater ICC of 0.300. System-consensus score divergence (SD = 9.5) was smaller than inter-expert divergence (SD = 12.4), with no directional bias (Wilcoxon p = 0.613). Protocol Design showed the strongest category-level agreement (ICC = 0.551); Academic Writing showed a negative ICC (-0.567), reflecting a structural rubric-expert mismatch. Conclusions: Domain-specific pre-deployment audit may provide a practical foundation for governing medical research agent skills, complementing general-purpose quality checks with structured audit workflows tailored to scientific use cases.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20441
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills
Hou, Yingyong
Lao, Xinyuan
Wang, Huimei
Yao, Qianyu
Chen, Wei
Huang, Bocheng
Sun, Fei
Lv, Yuxian
Lei, Weiqi
Wen, Xueqian
Xia, Pengfei
Tan, Zhujun
Xie, Shengyang
Artificial Intelligence
Background: Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safeguards beyond general-purpose evaluation, including scientific integrity, methodological validity, reproducibility, and boundary safety. This study developed and preliminarily evaluated a domain-specific audit framework for medical research agent skills, with a focus on reliability against expert review. Methods: We developed MedSkillAudit (skill-auditor@1.0), a layered framework assessing skill release readiness before deployment. We evaluated 75 skills across five medical research categories (15 per category). Two experts independently assigned a quality score (0-100), an ordinal release disposition (Production Ready / Limited Release / Beta Only / Reject), and a high-risk failure flag. System-expert agreement was quantified using ICC(2,1) and linearly weighted Cohen's kappa, benchmarked against the human inter-rater baseline. Results: The mean consensus quality score was 72.4 (SD = 13.0); 57.3% of skills fell below the Limited Release threshold. MedSkillAudit achieved ICC(2,1) = 0.449 (95% CI: 0.250-0.610), exceeding the human inter-rater ICC of 0.300. System-consensus score divergence (SD = 9.5) was smaller than inter-expert divergence (SD = 12.4), with no directional bias (Wilcoxon p = 0.613). Protocol Design showed the strongest category-level agreement (ICC = 0.551); Academic Writing showed a negative ICC (-0.567), reflecting a structural rubric-expert mismatch. Conclusions: Domain-specific pre-deployment audit may provide a practical foundation for governing medical research agent skills, complementing general-purpose quality checks with structured audit workflows tailored to scientific use cases.
title MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills
topic Artificial Intelligence
url https://arxiv.org/abs/2604.20441