IJCAI 20260 citations

vSpeedUI: Turning Past GUI Experience into Fast Executable Plans

Xiaohan Zheng, Yihong Chen, Haiquan Qiu, Quanming Yao

Abstract

LLM-based mobile GUI agents usually invoke large models for nearly every micro-action, making real-device automation slow even when similar workflows have been completed before. We present vSpeedUI, a public demo system that turns past GUI experience into fast executable plans. It organizes historical trajectories into an Executable Experience Graph (EXG), where UI states are connected by Semantic Step Summaries with explicit preconditions. At task initialization, vSpeedUI performs Global Look-ahead Planning to retrieve, validate, and rank candidate transitions into a pre-verified plan. During execution, the agent uses lightweight graph traversal with state localization, target adaptation, and fallback when needed. On HarmonyOS, vSpeedUI reduces LLM latency and total task time while maintaining strong success rates, showing a practical route toward data-efficient GUI automation. Code is available at: https://github.com/LARS-research/vSpeedUI.

AI: Agent-based and Multi-agent SystemsAI: Planning and SchedulingAI: Knowledge Representation and ReasoningAI: Machine Learning
BibTeX
@inproceedings{ijcai2026_vspeeduiturningp,
  title = {vSpeedUI: Turning Past GUI Experience into Fast Executable Plans},
  author = {Xiaohan Zheng and Yihong Chen and Haiquan Qiu and Quanming Yao},
  booktitle = {IJCAI 2026},
  year = {2026}
}
vSpeedUI: Turning Past GUI Experience into Fast Executable Plans · IJCAI 2026