MobiFlow: Real-World Mobile Agent Benchmarking through Trajectory Fusion

Computer Science > Artificial Intelligence [Submitted on 28 Feb 2026] MobiFlow: Real-World Mobile Agent Benchmarking through Trajectory Fusion Yunfei Feng, Xi Zhao, Cheng Zhang, Dahu Feng, Daolin Cheng, Jianqi Yu, Yubin Xia, Erhu Feng Mobile agents can autonomously complete user-assigned tasks through GUI interactions. However, existing mainstream evaluation benchmarks, such as AndroidWorld, operate by connecting to a system-level Android emulator and provide evaluation signals based on the state of system resources. In real-world mobile-agent scenarios, however, many third-party applications do not expose system-level APIs to determine whether a task has succeeded, leading to a mismatch between benchmarks and real-world usage and making it difficult to evaluate model performance accurately. To address these issues, we propose MobiFlow, an evaluation framework built on tasks drawn from arbitrary third-party applications. Using an efficient graph-construction algorithm based on multi-trajectory fusion, MobiFlow can effectively compress the state space, support dynamic interaction, and better align with real-world third-party application scenarios. MobiFlow covers 20 widely used third-party applications and comprises 240 diverse real-world tasks, with enriched evaluation metrics. Compared with AndroidWorld, MobiFlow's evaluation results show higher alignment with human assessments and can guide the training of future GUI-based models under real workloads. Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE) Cite as: arXiv:2604.09587 [cs.AI]   (or arXiv:2604.09587v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.09587 Focus to learn more Submission history From: Erhu Feng [view email] [v1] Sat, 28 Feb 2026 14:30:33 UTC (4,860 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.LG cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)