# Feed-O-Meter: Investigating AI-Generated Mentee Personas as Interactive Agents for Scaffolding Design Feedback Practice

arXiv: https://arxiv.org/abs/2509.07424 · HTML: https://mlsanity.com/paper/2509.07424/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 89 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 16 of 16)

- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Homogenization Effects of Large Language Models on Human Creative Ideation](https://mlsanity.com/paper/2402.01536/) (2024)
- [Rehearsal: Simulating Conflict to Teach Conflict Resolution](https://mlsanity.com/paper/2309.12309/) (2023)
- [Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education](https://mlsanity.com/paper/2309.14534/) (2023)
- [The Effects of Generative AI on Design Fixation and Divergent Thinking](https://mlsanity.com/paper/2403.11164/) (2024)
- [LLM-as-a-tutor in EFL Writing Education: Focusing on Evaluation of Student-LLM Interaction](https://mlsanity.com/paper/2310.05191/) (2023)
- [RECIPE: How to Integrate ChatGPT into EFL Writing Education](https://mlsanity.com/paper/2305.11583/) (2023)
- [Help Me Reflect: Leveraging Self-Reflection Interface Nudges to Enhance Deliberativeness on Online Deliberation Platforms](https://mlsanity.com/paper/2401.10820/) (2024)
- [SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agent](https://mlsanity.com/paper/2502.08599/) (2025)
- [A Comparison of Inquiry-Based Conceptual Feedback vs. Traditional Detailed Feedback Mechanisms in Software Testing Education: An Empirical Investigation](https://mlsanity.com/paper/2011.13004/) (2020)
- [Hardhats and Bungaloos: Comparing Crowdsourced Design Feedback with Peer Design Feedback in the Classroom](https://mlsanity.com/paper/2101.09161/) (2021)
- [Understanding and Supporting Peer Review Using AI-reframed Positive Summary](https://mlsanity.com/paper/2503.10264/) (2025)
- [Nudge for Deliberativeness: How Interface Features Influence Online Discourse](https://mlsanity.com/paper/2001.04612/) (2020)
- [Ask Me or Tell Me? Enhancing the Effectiveness of Crowdsourced Design Feedback](https://mlsanity.com/paper/2101.06143/) (2021)
- [DesignQuizzer: A Community-Powered Conversational Agent for Learning Visual Design](https://mlsanity.com/paper/2310.12019/) (2023)
- [Identify Design Problems Through Questioning: Exploring Role-playing Interactions with Large Language Models to Foster Design Questioning Skills](https://mlsanity.com/paper/2409.07178/) (2024)

## Abstract (arXiv)

Effective feedback, including critique and evaluation, helps designers develop design concepts and refine their ideas, supporting informed decision-making throughout the iterative design process. However, in studio-based design courses, students often struggle to provide feedback due to a lack of confidence and fear of being judged, which limits their ability to develop essential feedback-giving skills. Recent advances in large language models (LLMs) suggest that role-playing with AI agents can let learners engage in multi-turn feedback without the anxiety of external judgment or the time constraints of real-world settings. Yet prior studies have raised concerns that LLMs struggle to behave like real people in role-play scenarios, diminishing the educational benefits of these interactions. Therefore, designing AI-based agents that effectively support learners in practicing and developing intellectual reasoning skills requires more than merely assigning the target persona's personality and role to the agent. By addressing these issues, we present Feed-O-Meter, a novel system that employs carefully designed LLM-based agents to create an environment in which students can practice giving design feedback. The system enables users to role-play as mentors, providing feedback to an AI mentee and allowing them to reflect on how that feedback impacts the AI mentee's idea development process. A user study (N=24) indicated that Feed-O-Meter increased participants' engagement and motivation through role-switching and helped them adjust feedback to be more comprehensible for an AI mentee. Based on these findings, we discuss future directions for designing systems to foster feedback skills in design education.