GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations Paper • 2610.22708 • Published 20 days ago • 6
FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows Paper • 2608.21460 • Published Aug 20
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL Paper • 2607.16204 • Published May 7 • 7
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis Paper • 2601.20103 • Published Jan 27 • 2
GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations Paper • 2610.22708 • Published 20 days ago • 6