GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation

TL;DR

GUI-Rise introduces a structured reasoning framework with history summarization to improve GUI navigation by enhancing generalization and decision-making, achieving state-of-the-art results especially in out-of-domain tasks.

Contribution

The paper presents a novel reasoning-enhanced framework and GUI-Rise agent that integrate structured reasoning, history summarization, and reinforcement learning for improved GUI navigation.

Findings

State-of-the-art performance on standard benchmarks.

Strong out-of-domain generalization.

Effective history-aware action prediction.

Abstract

While Multimodal Large Language Models (MLLMs) have advanced GUI navigation agents, current approaches face limitations in cross-domain generalization and effective history utilization. We present a reasoning-enhanced framework that systematically integrates structured reasoning, action prediction, and history summarization. The structured reasoning component generates coherent Chain-of-Thought analyses combining progress estimation and decision reasoning, which inform both immediate action predictions and compact history summaries for future steps. Based on this framework, we train a GUI agent, \textbf{GUI-Rise}, through supervised fine-tuning on pseudo-labeled trajectories and reinforcement learning with Group Relative Policy Optimization (GRPO). This framework employs specialized rewards, including a history-aware objective, directly linking summary quality to subsequent action performance. Comprehensive evaluations on standard benchmarks demonstrate state-of-the-art results under identical training data conditions, with particularly strong performance in out-of-domain scenarios. These findings validate our framework's ability to maintain robust reasoning and generalization across diverse GUI navigation tasks. Code is available at https://leon022.github.io/GUI-Rise.