Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions
Xiaokai Yan, Jingtao Ding, Yong Li, Zhiwen Yu
Abstract
Mobile GUI Agents powered by multimodal large language models (MLLMs) show promise in human-computer intelligence. However, current research primarily focuses on reactive task execution while lacking a comprehensive "understandingprediction-execution" process for user intentions, which are the core requirements of active agents. In this paper, we propose the Act2Intention framework that builds an active mobile agent by integrating understanding, predicting user intentions, and executing decisions. Firstly, we constructed the Act2Intention Bench through collection and validated generation, comprising 72,511 intentions and over 700,000 actions across 52 apps, thereby establishing the first benchmark for evaluating proactive agents via continuous "intention-actions" trajectories. We further develop the Act2Intention Agent, achieving proactive services through Proactive-oriented Intention Understanding, Personalized Proactive Intention Prediction, and Experienceguided Intention Execution. Experimental results show that supervised fine-tuning on Act2Intention Bench yields absolute improvements of +32.0 Acc-S, +10.25 Acc-S, and +6.9 SSR points over non-fine-tuned counterparts under the same agent framework for intention understanding, prediction, and execution, respectively. This success underscores the necessity and value of the Act2Intention Bench, which establishes a standardized platform for developing and evaluating proactive agents and consequently paves the way for research on intention-driven human-computer interaction. To facilitate further research, we open-source our code and Act2Intention Bench at: npuNancy/Act2Intention.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration cites AutoDroid: LLM-powered Task Automation in Android
- UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning cites Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
Builds on29
- Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent CollaborationJunyang Wang, Haiyang Xu, Haitao Jia, Xi Zhang et al.NeurIPS 2024 · 245 citations
- ProAgent: Building Proactive Cooperative Agents with Large Language ModelsCeyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang et al.AAAI 2024 · 141 citations
- OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisQiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin et al.ACL 2025 · 114 citations
- UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement LearningZhengxi Lu, Yuxiang Chai, Yaxuan Guo, Xi Yin et al.AAAI 2026 · 103 citations
- AutoDroid: LLM-powered Task Automation in AndroidHao Wen, Yuanchun Li, Guohong Liu, Shanhui Zhao et al.MobiCom 2024 · 94 citations
Related papers
- FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM AgentsQinglong Yang, Haoming Li, Haotian Zhao, Xiaokai Yan et al.ICLR 2026 · 21 citations
- ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence On Mobile DevicesDezhi Kong, Zhengzhao Feng, Qiliang Liang, Hao Wang et al.CVPR 2026 · 6 citations
- Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile AgentsShihan Deng, Weikai Xu, Hongda Sun, Wei Liu et al.ACL 2024 · 10 citations
- Spa-Bench: a comprehensive Benchmark for Smartphone Agent EvaluationJingxuan Chen, Derek Yuen, Bin Xie, Yuhao Yang et al.ICLR 2025
- ContextAgent: Context-Aware Proactive LLM Agents with Open-world Sensory PerceptionsBufang Yang, Lilin Xu, Liekang Zeng, Kaiwei Liu et al.NeurIPS 2025 · 68 citations
