Communication-Efficient Desire Alignment for Embodied Agent-Human Adaptation
Yuanfei Wang, Xinju Huang, Fangwei Zhong, Yaodong Yang, Yizhou Wang, Yuanpei Chen, Hao Dong

TL;DR
This paper introduces FAMER, a framework that improves desire understanding and communication efficiency for embodied agents collaborating with humans, enabling faster adaptation to user goals in complex environments.
Contribution
The paper presents a novel desire-based mental reasoning framework, reflection-based communication, and memory integration for desire alignment in embodied agents.
Findings
Enhanced task success rate with desire alignment
Reduced communication rounds for goal clarification
Improved adaptation speed in complex environments
Abstract
While embodied agents have made significant progress in performing complex physical tasks, real-world applications demand more than pure task execution. The agents must collaborate with unfamiliar agents and human users, whose goals are often vague and implicit. In such settings, interpreting ambiguous instructions and uncovering underlying desires is essential for effective assistance. Therefore, fast and accurate desire alignment becomes a critical capability for embodied agents. In this work, we first develop a home assistance simulation environment HA-Desire that integrates an LLM-driven proxy human user exhibiting realistic value-driven goal selection and communication. The ego agent must interact with this proxy user to infer and adapt to the user's latent desires. To achieve this, we present a novel framework FAMER for fast desire alignment, which introduces a desire-based mental…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics
