Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short Paper • 2606.09380 • Published about 1 month ago • 9
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published May 28 • 144
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection Paper • 2605.30189 • Published May 28 • 9
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 250
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers Paper • 2603.24414 • Published Mar 25 • 183