Saved in:
Bibliographic Details
Main Authors: Wang, Ziwei, Zheng, Junjie, Yang, Leyang, Zhou, Sheng, Tang, Xiaoxuan, Fang, Zhouhua, Liu, Zhiwei, Chen, Dajun, Li, Yong, Bu, Jiajun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.13488
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911594670194688
author Wang, Ziwei
Zheng, Junjie
Yang, Leyang
Zhou, Sheng
Tang, Xiaoxuan
Fang, Zhouhua
Liu, Zhiwei
Chen, Dajun
Li, Yong
Bu, Jiajun
author_facet Wang, Ziwei
Zheng, Junjie
Yang, Leyang
Zhou, Sheng
Tang, Xiaoxuan
Fang, Zhouhua
Liu, Zhiwei
Chen, Dajun
Li, Yong
Bu, Jiajun
contents Autonomous Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) enable digital automation on end-user devices. While scaling both parameters and data has yielded substantial gains, advanced methods still suffer from prohibitive deployment costs on resource-constrained devices. When facing complex in-the-wild scenarios, lightweight GUI agents are bottlenecked by limited capacity and poor task scalability under end-to-end episodic learning, impeding adaptation to multi-agent systems (MAS), while training multiple skill-specific experts remains costly. Can we strike an effective trade-off in this cost-scalability dilemma, enabling lightweight MLLMs to participate in realistic GUI workflows? To address these challenges, we propose the LAMO framework, which endows a lightweight MLLM with GUI-specific knowledge and task scalability, allowing multi-role orchestration to expand its capability boundary for GUI automation. LAMO combines role-oriented data synthesis with a two-stage training recipe: (i) supervised fine-tuning with Perplexity-Weighted Cross-Entropy optimization for knowledge distillation and visual perception enhancement, and (ii) reinforcement learning for role-oriented cooperative exploration. With LAMO, we develop a task-scalable native GUI agent, LAMO-3B, supporting monolithic execution and MAS-style orchestration. When paired with advanced planners as a plug-and-play policy executor, LAMO-3B can continuously benefit from planner advances, enabling a higher performance ceiling. Extensive static and online evaluations validate the effectiveness of our design.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13488
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Scalable Lightweight GUI Agents via Multi-role Orchestration
Wang, Ziwei
Zheng, Junjie
Yang, Leyang
Zhou, Sheng
Tang, Xiaoxuan
Fang, Zhouhua
Liu, Zhiwei
Chen, Dajun
Li, Yong
Bu, Jiajun
Artificial Intelligence
Autonomous Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) enable digital automation on end-user devices. While scaling both parameters and data has yielded substantial gains, advanced methods still suffer from prohibitive deployment costs on resource-constrained devices. When facing complex in-the-wild scenarios, lightweight GUI agents are bottlenecked by limited capacity and poor task scalability under end-to-end episodic learning, impeding adaptation to multi-agent systems (MAS), while training multiple skill-specific experts remains costly. Can we strike an effective trade-off in this cost-scalability dilemma, enabling lightweight MLLMs to participate in realistic GUI workflows? To address these challenges, we propose the LAMO framework, which endows a lightweight MLLM with GUI-specific knowledge and task scalability, allowing multi-role orchestration to expand its capability boundary for GUI automation. LAMO combines role-oriented data synthesis with a two-stage training recipe: (i) supervised fine-tuning with Perplexity-Weighted Cross-Entropy optimization for knowledge distillation and visual perception enhancement, and (ii) reinforcement learning for role-oriented cooperative exploration. With LAMO, we develop a task-scalable native GUI agent, LAMO-3B, supporting monolithic execution and MAS-style orchestration. When paired with advanced planners as a plug-and-play policy executor, LAMO-3B can continuously benefit from planner advances, enabling a higher performance ceiling. Extensive static and online evaluations validate the effectiveness of our design.
title Towards Scalable Lightweight GUI Agents via Multi-role Orchestration
topic Artificial Intelligence
url https://arxiv.org/abs/2604.13488