AIJan 29

BEAP-Agent: Backtrackable Execution and Adaptive Planning for GUI Agents

arXiv:2601.21352v1h-index: 2
Originality Incremental advance
AI Analysis

This addresses a critical recovery issue for GUI automation agents, offering a systematic solution for long-horizon tasks, though it appears incremental in improving existing methods.

The paper tackles the problem of GUI agents failing to recover from incorrect exploration paths by proposing BEAP-Agent, a DFS-based framework with backtracking and adaptive planning, achieving 28.2% accuracy on the OSWorld benchmark.

GUI agents are designed to automate repetitive tasks and enhance productivity. However, existing GUI agents struggle to recover once they follow an incorrect exploration path, often leading to task failure. In this work, we model GUI task execution as a DFS process and propose BEAP-Agent, a DFS-based framework that supports long-range, multi-level state backtracking with dynamic task tracking and updating. The framework consists of three collaborative components: Planner, Executor, and Tracker. Together, they enable effective task exploration and execution. BEAP-Agent fills the gap in systematic backtracking mechanisms for GUI agents, offering a systematic solution for long-horizon task exploration. We conducted a systematic evaluation on the OSWorld benchmark, where BEAP-Agent achieved an accuracy of 28.2%, validating the effectiveness of the proposed method.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes