Tianzhuo Yang

The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a pervasive issue across current systems.

SafeMCP is a server-side defense plugin that uses look-ahead reasoning to proactively filter and constrain tool acquisition for LLM agents, thereby mitigating catastrophic risks associated with expanding action spaces.