Xingrui Yu

Advancing from usable to collaborative autonomy requires driving systems to execute passenger instructions safely and reliably. This work formulates instruction realization as scheduling across multiple motion planners and presents a dual-loop framework that provides a transparent decision chain...

Autonomous LLM agents are increasingly deployed in complex environments as tool-using systems. However, their safety remains fragile, as minor reasoning or retrieval errors can be amplified into hazardous actions within the agentic workflow. Existing defenses, often limited to static prompts or p...