SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World

TL;DR

This paper introduces SmartAgent, a novel embodied reasoning framework that incorporates personalized user preferences through a chain-of-thought process, demonstrated on a new dataset for personalized agent tasks.

Contribution

It proposes the Chain-of-User-Thought paradigm and the SmartAgent framework, pioneering personalized embodied agent reasoning in cyber environments.

Findings

SmartAgent effectively interacts with GUI and accesses item pools.

SmartAgent generates explicit user requirements from previous actions.

SmartAgent recommends items aligning with implicit user preferences.

Abstract

Recent advances in embodied agents with multimodal perception and reasoning capabilities based on large vision-language models (LVLMs), excel in autonomously interacting either real or cyber worlds, helping people make intelligent decisions in complex environments. However, the current works are normally optimized by golden action trajectories or ideal task-oriented solutions toward a definitive goal. This paradigm considers limited user-oriented factors, which could be the reason for their performance reduction in a wide range of personal assistant applications. To address this, we propose Chain-of-User-Thought (COUT), a novel embodied reasoning paradigm that takes a chain of thought from basic action thinking to explicit and implicit personalized preference thought to incorporate personalized factors into autonomous agent learning. To target COUT, we introduce SmartAgent, an agent framework perceiving cyber environments and reasoning personalized requirements as 1) interacting with GUI to access an item pool, 2) generating users' explicit requirements implied by previous actions, and 3) recommending items to fulfill users' implicit requirements. To demonstrate SmartAgent's capabilities, we also create a brand-new dataset SmartSpot that offers a full-stage personalized action-involved environment. To our best knowledge, our work is the first to formulate the COUT process, serving as a preliminary attempt towards embodied personalized agent learning. Our extensive experiments on SmartSpot illuminate SmartAgent's functionality among a series of embodied and personalized sub-tasks. We will release code and data upon paper notification at https://github.com/tsinghua-fib-lab/SmartAgent.