LiteGUI：通过多解引导蒸馏与双层强化学习构建轻量级 GUI 智能体

View PDF HTML (experimental)

Abstract:We present LiteGUI, a new framework for building lightweight GUI agents. GUI interaction poses unique challenges due to the long-horizon nature of complex tasks and the existence of multiple valid interaction paths, which are difficult for lightweight GUI agents to handle effectively. To address these challenges, LiteGUI introduces a two-stage post-training framework operating on logged GUI states. First, we propose Guided On-Policy Distillation, which provides training-time privileged teacher guidance at each GUI state by selecting the most-matched valid action from human-verified multi-solution action annotations, while leaving the student's on-policy rollout unchanged. Second, we develop Multi-Solution Dual-Level GRPO, which combines action-level supervision with history-conditioned, per-state planning-quality supervision while accounting for multiple valid actions at each logged GUI state. Together, these stages support multi-step GUI tasks without requiring the student to reproduce fixed demonstration trajectories. We further develop a scalable data generation pipeline and a corresponding multi-solution dataset, Lite-Dataset, to support the training and evaluation of GUI agents, addressing a gap in the existing literature. Extensive experiments across multiple GUI benchmarks demonstrate that LiteGUI substantially improves the performance of lightweight GUI agents over existing training paradigms, including SFT, on-policy distillation and GRPO, and achieves competitive or superior performance compared with substantially larger models.

Subjects:	Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2605.07505 [cs.AI]
	(or arXiv:2605.07505v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2605.07505 arXiv-issued DOI via DataCite

Submission history

From: Yubin Wu [view email]
[v1] Fri, 8 May 2026 09:38:29 UTC (322 KB)
[v2] Thu, 8 Oct 2026 08:52:00 UTC (356 KB)