Reproduce “Socratic: Enhancing Human Teamwork via AI-enabled Coaching” 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
Sangwon Seo, Bing Han, Rayan E. Harari, Roger D. Dias, Marco A. Zenati, Eduardo Salas, Vaibhav Unhelkar
A research group from Rice University and Harvard Medical School developed Socratic, an AI system that provides real-time, in-task coaching to human teams. It uses learned behavioral models to infer team members' intents and delivers targeted interventions, demonstrably improving team performance in collaborative tasks with minimal interruptions while maintaining high user acceptance.
Key insights
- AI can effectively learn latent intent-driven human team behaviors from limited, semi-supervised data for real-time inference.
- Proactive, real-time AI coaching based on inferred cognitive states can enhance human team performance in complex, dynamic tasks.
- Interventions should be targeted and value-based to minimize disruption while maximizing benefits, fostering user acceptance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.