AIRA_2: Boosting AI Research Agent Performance
Discover how AIRA_2 overcomes AI research bottlenecks with multi-GPU execution, stable evaluation, and adaptive agents for superior results.
GUIDE: Fixing Domain Bias in GUI Agents with Web Videos
Discover how GUIDE uses real-time web video retrieval and annotation to resolve domain bias in GUI agents, boosting performance without retraining models.
Semi-Automated Knowledge Engineering for Airport Management
Discover how semi-automated knowledge engineering improves process mapping and efficiency in Total Airport Management.
AutoB2G: AI-Driven Framework for Building-Grid Co-Simulation
Discover AutoB2G, an AI-powered framework using large language models for automated building-grid co-simulation and smarter energy management.
BeSafe-Bench: Benchmarking Safety Risks in Autonomous Agents
Discover BeSafe-Bench, a new benchmark exposing behavioral safety risks in situated autonomous agents across web, mobile, and embodied environments.