TuringSpace: Grounding Spatial Intelligence in Action with Interactive CAPTCHAs Paper • 2611.25387 • Published 3 days ago • 24
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements Paper • 2611.03126 • Published 19 days ago • 51
Agent World Model in the Wild: Computer-Use Agent Environment Synthesis Paper • 2610.26828 • Published Oct 19 • 72
Self-Evolving Coding Agents via Harness-Policy Optimization Paper • 2610.22791 • Published Oct 16 • 50
Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL Paper • 2610.21439 • Published Oct 15 • 29
GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction Paper • 2604.23941 • Published Apr 27 • 6
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents Paper • 2604.10577 • Published Apr 12 • 27
Video-Based Reward Modeling for Computer-Use Agents Collection A collection of models and datasets from the paper "Video-Based Reward Modeling for Computer-Use Agents". Github: https://github.com/limenlp/ExeVRM • 3 items • Updated Apr 1 • 1
Code2World: A GUI World Model via Renderable Code Generation Paper • 2602.09856 • Published Feb 10 • 176
MARS: Modular Agent with Reflective Search for Automated AI Research Paper • 2602.02660 • Published Feb 2 • 67
Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning Paper • 2510.23473 • Published Oct 27, 2025 • 87
Less is More: Recursive Reasoning with Tiny Networks Paper • 2510.04871 • Published Oct 6, 2025 • 520