ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 4 days ago • 240
Watch Before You Answer: Learning from Visually Grounded Post-Training Paper • 2604.05117 • Published 7 days ago • 32
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Paper • 2604.05015 • Published 7 days ago • 227
AI Paper of the Day Collection A collection of papers that I think are interesting, one added each day • 636 items • Updated 1 day ago • 96
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use Paper • 2509.01055 • Published Sep 1, 2025 • 81
EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning Paper • 2603.12698 • Published about 1 month ago • 1
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks Paper • 2603.27862 • Published 14 days ago • 30
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use Paper • 2510.05592 • Published Oct 7, 2025 • 110