Reproduce “Personalized Affective Perception via Continual Learning in Human-Agent Negotiation” 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
Mehmet Onur Keskin, Berk Buzcu, Nikhil Churamani, Reyhan Aydogan, Hatice Gunes, Catholijn Jonker
The authors present a robot negotiation system that adapts its interpretation of a participant’s facial valence and arousal and uses changes in those estimates to adjust bargaining targets. In 66 paired university-student comparisons, the combined demo-initialized and online-adapting CLIFER condition produced higher agent utility than fixed FaceChannel, alongside more participant concessions. The study does not establish recognition accuracy or isolate online adaptation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.