What Platform Scores Miss: Multidimensional Evaluation of AI Teaching Agents in Medical Education
Hui Zhang, Lihui Qu, Jianmin Zheng, Yi Xiong, Hongbo Bai, Ruiying Ji, Guohui Liu, Wanling Chen, Zirui Cheng, Youbang Chen, Chun-tao Yang · 2026
Read What Platform Scores Miss: Multidimensional Evaluation of AI Teaching Agents in Medical Education by Hui Zhang, Lihui Qu, Jianmin Zheng, Yi Xiong, Hongbo Bai, Ruiying Ji, Guohui Liu, Wanling Chen, Zirui Cheng, Youbang Chen, Chun-tao Yang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13540620.txt.
Description
Hui Zhang and ten co-authors test what sales scores miss in AI teach hands for med school. Their study appeared in twenty twenty-six. Eight AI hands taught a gland class span in four play roles. Twenty-two fourth-year students made one hundred sixty-seven talks, each scored by the sales side and by a plain eight-part rubric, with an expert re-check on a slice.
Sales and rubric ranks split for most hands: one sales star sat last on true grade, and a sales mid hand sat first. Hands split most on grasp span and least on play worth. Weak aim set was shared. AI grades tied with the expert in whole.
Catalog record
| CREATOR | Hui Zhang, Lihui Qu, Jianmin Zheng, Yi Xiong, Hongbo Bai, Ruiying Ji, Guohui Liu, Wanling Chen, Zirui Cheng, Youbang Chen, Chun-tao Yang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |