Brick-Composer: Using MLLMs for Assembly with Diverse Bricks Paper • 2606.05445 • Published 7 days ago • 7
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints Paper • 2606.05622 • Published 6 days ago • 40
UserBench: An Interactive Gym Environment for User-Centric Agents Paper • 2507.22034 • Published Jul 29, 2025 • 30