CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding
Paper
•
2501.09645
•
Published
•
1
AI Agents, LLM Planning and Reasoning, Human-Computer Interaction, LLM Memory, Safety & Guardrails
CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty