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

🏛 Institutions: Chengdu Institute of Computer Applications , CAS , University of Chinese Academy of Sciences , Tencent Turing Lab , Georgia Tech , Tsinghua , Nankai University , Shenzhen Loop Area Institute
📅 Date: January 26, 2026
📑 Publisher: ICLR 2026 (Poster)
💻 Env: General GUI
🔑 Keywords: framework benchmark long-horizon tasks reflection rollback LongGUIBench LongHorizonUI

TLDR

LongHorizonUI targets error accumulation in long-horizon GUI control by combining indexed multimodal perception, structured reflective decision-making, and rollback-based compensatory execution. It also introduces LongGUIBench for tasks longer than 15 steps across games and complex applications, and reports substantial gains on long-horizon evaluation while staying competitive on public benchmarks.

Open paper Report issue