TensorX
返回文献探索

Paper · arXiv 2502.14282

PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC

Haowei Liu, Xi Zhang, Haiyang Xu, Yuyang Wanyan, Junyang Wang, Ming Yan, Ji Zhang, Chunfeng Yuan, Changsheng Xu, Weiming Hu, Fei Huang

29 upvotesFebruary 20, 2025arXiv 预印本
AI 摘要

A hierarchical agent framework called PC-Agent is proposed to improve the performance of MLLM-based GUI agents in complex PC environments through better perception and decision-making processes.

Active Perception Module (APM)hierarchical multi-agent collaborationInstruction-Subtask-Action levelsManagerProgressDecisionReflection agentPC-Eval

Abstract

In the field of MLLM-based GUI agents, compared to smartphones, the PC scenario not only features a more complex interactive environment, but also involves more intricate intra- and inter-app workflows. To address these issues, we propose a hierarchical agent framework named PC-Agent. Specifically, from the perception perspective, we devise an Active Perception Module (APM) to overcome the inadequate abilities of current MLLMs in perceiving screenshot content. From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hierarchical multi-agent collaboration architecture that decomposes decision-making processes into Instruction-Subtask-Action levels. Within this architecture, three agents (i.e., Manager, Progress and Decision) are set up for instruction decomposition, progress tracking and step-by-step decision-making respectively. Additionally, a Reflection agent is adopted to enable timely bottom-up error feedback and adjustment. We also introduce a new benchmark PC-Eval with 25 real-world complex instructions. Empirical results on PC-Eval show that our PC-Agent achieves a 32% absolute improvement of task success rate over previous state-of-the-art methods. The code will be publicly available.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号