Self-Evolving Coding Agents via Harness-Policy Optimization Paper • 2610.22791 • Published 6 days ago • 46
Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL Paper • 2610.21439 • Published 7 days ago • 43
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
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents Paper • 2604.10577 • Published Apr 12 • 27