AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI Agent

Bin Kang, Shaoguo Wen, Yifei Bi, Shunlong Wu, Xinbin Yuan, Rui Shao, Junle Wang, Zhuotao Tian

ICLR 2026 · Multi-agent systems and games › LLM agents · approach: GUI agent memory and trajectories

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes LongHorizonUI, a unified framework to improve the robustness and sustained reliability of MLLM-based GUI agents on long-horizon tasks in dynamic environments.

Problem

MLLM-based GUI agents perform well on short-term GUI tasks but lack robustness on complex long-horizon tasks in dynamic environments.

Approach

A unified framework intended to overcome core limitations of existing GUI agents for sustained reliability over long-horizon tasks; specific mechanism not stated in the abstract provided.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use LongHorizonUI instead of UI-TARS-1.5GUI agent · LongGUIBench General-HighSR: 21.8 -> 52.3Improved
use LongHorizonUI instead of UI-TARS-1.5GUI agent · LongGUIBench Game-LowSR: 69.5 -> 83.9Improved
use LongHorizonUI instead of InfiGUI-R1GUI agent · ScreenSpotavg accuracy: 87.5 -> 90.4Improved
use LongHorizonUI instead of UI-TARS-7BGUI agent · ScreenSpot-V2avg accuracy: 84.7 -> 86.2Improved
use LongHorizonUI instead of GUI-R1-7BGUI agent · AndroidControl and GUI-Odysseyavg TM/SR: 63.2 -> 65.5Improved
use LongHorizonUI instead of UI-TARS-72BGUI agent · OSWorld 50 stepssuccess rate: 24.6 -> 29.4Improved
add the icon detector to the perceiver (ablation)Multimodal Enhanced Perceiver · LongGUIBenchstep-completion rate: +6.1%Improved
add OCR to the perceiver (ablation)Multimodal Enhanced Perceiver · LongGUIBenchstep-completion rate: +2.3%Improved
add relative-coordinate fallback to index execution (ablation)Compensating Action Executor · LongGUIBenchtask completion: 81.4 -> +1.2%Improved
add absolute-coordinate fallback to index execution (ablation)Compensating Action Executor · LongGUIBenchtask completion: 81.4 -> +2.5%Improved
add historical-coordinate fallback to index execution (ablation)Compensating Action Executor · LongGUIBenchtask completion: 81.4 -> +3.9%Improved
raise IoU merge threshold from 0.6 to 0.8 (ablation)Perceiver · LongGUIBenchtask success rate: 82.7 -> 83.9Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy