OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
From Daily Paper Cast by Jingwen Liang, Gengyu Wang
April 24, 2026 · 27 min · Episode 1797
About this episode
The episode discusses the development of OpenMobile, an open-source framework for synthesizing task instructions and agent trajectories in mobile agents.
🤗 Upvotes: 26 | cs.AI, cs.CL, cs.CV, cs.HC Authors: Kanzhi Cheng, Zehao Li, Zheng Ma, Nuo Chen, Jialin Cao, Qiushi Sun, Zichen Ding, Fangzhi Xu, Hang Yan, Jiajun Chen, Anh Tuan Luu, Jianbing Zhang, Lewei Lu, Dahua Lin Title: OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis Arxiv: http://arxiv.org/abs/2604.15093v1 Abstract: Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap, e.g., nearly 70% success on AndroidWorld. However, these systems keep their training data closed and remain opaque about their task and trajectory synthesis recipes. We present OpenMobile, an open-source framework that synthesizes high-quality task instructions and agent trajectories, with two key components: (1) The first is a scalable task synthesis pipeline that constructs a global environment memory from exploration, then leverages it to generate diverse and grounded instructions. and (2) a policy-switching strategy for trajectory rollout. By alternating between learner and expert models, it captures essential error-recovery data often missing in…
People in this episode
Hosts: Jingwen Liang, Gengyu Wang
Topics covered
- mobile agents
- vision-language models
- task synthesis
- trajectory synthesis
- open-source framework
Keywords
- OpenMobile
- mobile agents
- task synthesis
- trajectory synthesis
- vision-language models
- AndroidWorld
- Qwen2.5-VL
- Qwen3-VL
Mentioned in this episode
Books & works: OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
More episodes of Daily Paper Cast
- EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
- MiniMax Sparse Attention · June 13, 2026 · 26 min
- SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
- InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
- FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
- Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min
Explore listener stats, chart rankings, contacts and more on the Daily Paper Cast podcast page.