Reproduce “Feed-O-Meter: Investigating AI-Generated Mentee Personas as Interactive Agents for Scaffolding Design Feedback Practice” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hyunseung Lim, Dasom Choi, DaEun Choi, Sooyohn Nam, Hwajung Hong
Feed-O-Meter lets design students practice critique by mentoring an AI novice whose knowledge is limited to what they teach it. Its interface classifies and evaluates feedback, then shows the novice’s reactions and idea revisions. In a 24-person study, experts rated statements more specific, justified, and actionable with the full interface, but question quality and overall helpfulness did not improve significantly.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.