Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Paper • 2605.06130 • Published 11 days ago • 108
HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help? Paper • 2604.09408 • Published 19 days ago • 5
Structured Distillation of Web Agent Capabilities Enables Generalization Paper • 2604.07776 • Published Apr 9 • 22
Less Detail, Better Answers: Degradation-Driven Prompting for VQA Paper • 2604.04838 • Published Apr 6 • 13
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers Paper • 2603.24414 • Published Mar 25 • 183
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning Paper • 2603.04597 • Published Mar 4 • 210
Believe Your Model: Distribution-Guided Confidence Calibration Paper • 2603.03872 • Published Mar 4 • 40
UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? Paper • 2603.03241 • Published Mar 3 • 87