AI RESEARCH
Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions
arXiv CS.AI
•
ArXi:2605.26256v1 Announce Type: new Multimodal large language model (MLLM)-based embodied agents have shown strong potential for solving complex tasks in physical environments. However, personalized assistance requires than following generic instruction or recognizing object categories. In real-world scenarios, the intended target is often specified only implicitly through prior interactions, requiring agents to leverage personalized context accumulated over time.