"What Are You Doing?": Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing
Paper • 2602.15569 • Published • 13
AI Agents, LLM Planning and Reasoning, Human-Computer Interaction, LLM Memory, Safety & Guardrails
"What Are You Doing?": Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing
CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty