A Multi-Agent LLM Framework for Rating the Quality of Surgical Feedback

arXiv 2605.25440 ↗First posted 25 May 2026cs.CL cs.AI cs.MAcited by 1

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Verbal feedback delivered by attending surgeons in the operating room plays a critical formative role in resident trainee skill acquisition. Yet, assessing the quality of trainer feedback and its effectiveness in influencing trainee behavior during live surgery remains a challenge. Prior studies assessed feedback content relying on extensive manual annotation by expert human raters and focused on developing broad taxonomies that overlook the qualitative aspects of feedback delivery such as clarity or urgency. Limited existing automated methods, including keyword analysis and topic modeling, also fail to capture these nuanced aspects. We introduce a two-stage LLM-based framework that discovers interpretable feedback quality criteria grounded in the context of surgical training. Our method uses multi-agent prompting and surgical domain knowledge injection to discover a small set of human interpretable scoring criteria (e.g., Encouraging, Urgent, Clear). These criteria are then used to automatically score live surgical feedback via an LLM-as-a-judge approach. Evaluation on 4.2k trainer feedback instances demonstrates that our AI-discovered criteria outperform prior content-based frameworks in predicting feedback effectiveness, including observed trainee behavioral adjustments and trainer approval. This work advances scalable, human-aligned assessment of communication quality in the operating room and provides a foundation for improving surgical teaching practices.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 59 references that are in the map. First posted on arXiv 25 May 2026.

Builds on

13 of 59 references.

References · 13

2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,492
2022Large Language Models are Zero-Shot Reasonerscited by 4,348
2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,765
2024A Survey on LLM-as-a-Judgecited by 1,399
2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 792
2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 483
2024Homogenization Effects of Large Language Models on Human Creative Ideationcited by 127
2022Rationale-Augmented Ensembles in Language Modelscited by 111
2024Can You Trust LLM Judgments? Reliability of LLM-as-a-Judgecited by 53
2024Human-Centered Design Recommendations for LLM-as-a-Judgecited by 37
2022ThinkSum: Probabilistic reasoning over sets using large language modelscited by 23
2024OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language modelscited by 20

1 more

2024X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluationcited by 9

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 1.

1 paper.

2026On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performancecited by 0

Similar, not cited

Close in wording, no citation either way