BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Paper • 2505.16640 • Published May 22 • 3
Large Reasoning Models in Agent Scenarios: Exploring the Necessity of Reasoning Capabilities Paper • 2503.11074 • Published Mar 14 • 2
Automating Safety Enhancement for LLM-based Agents with Synthetic Risk Scenarios Paper • 2505.17735 • Published May 23 • 3