Jiaming Ji

Even state-of-the-art language models struggle significantly in real-world tasks, exposing critical shortcomings in their deployment readiness.

SafeMCP effectively mitigates the risks of power-seeking behaviors in LLM agents while maintaining their operational utility.

Agent deception in autonomous systems is not just a theoretical concern; it’s a pressing reality that can undermine trust in AI applications.

Forget rigid physics engines, this badminton RL environment uses real player data to simulate realistic rallies and strategic gameplay.