Improvisational Games Benchmark AI Social Intelligence
Explore how improvisational games like Connections benchmark AI agents' social intelligence through knowledge, summarization, and cognitive awareness.
Human-in-the-Loop Control for AI in CS Education
Explore human-in-the-loop methods to manage objective drift in AI-assisted computer science education and improve programming outcomes.
Safety-Aware Multi-Agent LLM for Behavioral Health Dialogue
Discover a safety-focused multi-agent LLM framework enhancing behavioral health communication through role orchestration and real-time safety monitoring.
OpenTools: Reliable Community Framework for AI Tool Agents
Discover OpenTools, a community-driven framework enhancing reliability in AI tool agents with standardized schemas, plug-and-play wrappers, and continuous...
CAMP: Adaptive Multi-Agent AI for Accurate Clinical Prediction
Discover CAMP, a case-adaptive multi-agent AI system improving clinical prediction accuracy with dynamic specialist panels and transparent decision-making.