REFINE: Real-world Exploration of Interactive Feedback and Student Behaviour
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917372266283008 |
|---|---|
| author | Fawzi, Fares Neshaei, Seyed Parsa Knezevic, Marta Nazaretsky, Tanya Käser, Tanja |
| author_facet | Fawzi, Fares Neshaei, Seyed Parsa Knezevic, Marta Nazaretsky, Tanya Käser, Tanja |
| contents | Formative feedback is central to effective learning, yet providing timely, individualised feedback at scale remains a persistent challenge. While recent work has explored the use of large language models (LLMs) to automate feedback, most existing systems still conceptualise feedback as a static, one-way artifact, offering limited support for interpretation, clarification, or follow-up. In this work, we introduce REFINE, a locally deployable, multi-agent feedback system built on small, open-source LLMs that treats feedback as an interactive process. REFINE combines a pedagogically-grounded feedback generation agent with an LLM-as-a-judge-guided regeneration loop using a human-aligned judge, and a self-reflective tool-calling interactive agent that supports student follow-up questions with context-aware, actionable responses. We evaluate REFINE through controlled experiments and an authentic classroom deployment in an undergraduate computer science course. Automatic evaluations show that judge-guided regeneration significantly improves feedback quality, and that the interactive agent produces efficient, high-quality responses comparable to a state-of-the-art closed-source model. Analysis of real student interactions further reveals distinct engagement patterns and indicates that system-generated feedback systematically steers subsequent student inquiry. Our findings demonstrate the feasibility and effectiveness of multi-agent, tool-augmented feedback systems for scalable, interactive feedback. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29142 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | REFINE: Real-world Exploration of Interactive Feedback and Student Behaviour Fawzi, Fares Neshaei, Seyed Parsa Knezevic, Marta Nazaretsky, Tanya Käser, Tanja Artificial Intelligence Human-Computer Interaction Formative feedback is central to effective learning, yet providing timely, individualised feedback at scale remains a persistent challenge. While recent work has explored the use of large language models (LLMs) to automate feedback, most existing systems still conceptualise feedback as a static, one-way artifact, offering limited support for interpretation, clarification, or follow-up. In this work, we introduce REFINE, a locally deployable, multi-agent feedback system built on small, open-source LLMs that treats feedback as an interactive process. REFINE combines a pedagogically-grounded feedback generation agent with an LLM-as-a-judge-guided regeneration loop using a human-aligned judge, and a self-reflective tool-calling interactive agent that supports student follow-up questions with context-aware, actionable responses. We evaluate REFINE through controlled experiments and an authentic classroom deployment in an undergraduate computer science course. Automatic evaluations show that judge-guided regeneration significantly improves feedback quality, and that the interactive agent produces efficient, high-quality responses comparable to a state-of-the-art closed-source model. Analysis of real student interactions further reveals distinct engagement patterns and indicates that system-generated feedback systematically steers subsequent student inquiry. Our findings demonstrate the feasibility and effectiveness of multi-agent, tool-augmented feedback systems for scalable, interactive feedback. |
| title | REFINE: Real-world Exploration of Interactive Feedback and Student Behaviour |
| topic | Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2603.29142 |