Strengthening an agent's empathic persona did not translate into broader knowledge delivery: the revised family-member agent had high role-play quality but the lowest knowledge coverage¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Agent A8, revised only in its prompt to strengthen an empathic family-member persona, attained role-play quality of 14.1 yet the lowest knowledge-point coverage (5.3) and lowest total score (60.6) of all agents. → Zhang Hui 2026

Evidence¶

Zhang Hui 2026¶

Zhang Hui, Qu Lihui, Zheng Jianmin, Xiong Yi, Bai Hongbo, Ji Ruiying, Liu Guohui, Chen Wanling, Cheng Zirui, Chen Youbang, Yang Chun-tao. (2026). What Platform Scores Miss: Multidimensional Evaluation of AI Teaching Agents in Medical Education. JMIR Medical Education. https://doi.org/10.2196/96819

q2 · i? · design · r2

Case-level observation of agent A8 after a prompt-only revision to strengthen empathy, with all other settings held constant; the article reports the dissociation between "role-play quality=14.1" and knowledge coverage of 5.3.

"it attained one of the highest role-play scores (role-play quality=14.1) yet the lowest knowledge-point coverage of all agents (knowledge-point coverage efficiency=5.3) and the lowest total score (60.6)."

Discussion¶

Related Claims¶

• AI teaching agents differed most on knowledge-related dimensions and least on role-play quality, with adaptive difficulty calibration a shared weakness — related
• Platform-generated scores and rubric-based teaching quality produced substantially divergent rankings of the same AI teaching agents — related
• The largest checklist-item gain from multi-agent scaffolding was in observable empathic expression, with additional gains in selected history-taking items — related