Could a shared dataset of real mobile apps accelerate ´vibe coding´ with large language models?

A public dataset of real mobile app UIs could transform how large language models tackle ´vibe coding´ and automate mobile workflows, says Droidrun’s creator.

As the Droidrun team undertakes the challenge of building an agent framework capable of autonomously navigating mobile apps through their real UI structure, a pivotal obstacle has emerged: the absence of a publicly accessible dataset that captures real Android app UI hierarchies, screen flows, and associated metadata. This gap in data not only hinders Droidrun but creates friction for the broader community working to empower large language models with a more grounded, context-rich understanding of mobile interfaces.

The founder poses a key question to the maker and developer community: would a comprehensive dataset aggregating real-world app UI trees, screen transitions, component types, and contextual metadata enable ´vibe coding´ agents to generalize more effectively across varied applications? Despite recent advancements, developing agents that intuitively interact with mobile UIs still requires significant manual tuning and repetition, as current models rely heavily on prompts and heuristics to ´feel right´ when navigating distinct app experiences. The lack of shared data keeps teams siloed and slows progress.

Envisioning a curated repository that spans categories like shopping, social, finance, and utilities, complete with detailed structural metadata—such as buttons, lists, inputs, navigation flows, and UX patterns—the author invites feedback: would access to such a dataset reduce the time spent on prompt tuning or help achieve more consistent agent alignment? Or, conversely, is the effort to amass this data unlikely to move the needle on reliable agent behavior? Community members are encouraged to share reflections, frustrations, and past experiences, potentially shaping the future of large language model-driven automation in mobile app contexts.

68

Impact Score

Saudi Artificial Intelligence startup launches Arabic LLM

Misraj Artificial Intelligence unveiled Kawn, an Arabic large language model, at AWS re:Invent and launched Workforces, a platform for creating and managing Artificial Intelligence agents for enterprises and public institutions.

Introducing Mistral 3: open artificial intelligence models

Mistral 3 is a family of open, multimodal and multilingual Artificial Intelligence models that includes three Ministral edge models and a sparse Mistral Large 3 trained with 41B active and 675B total parameters, released under the Apache 2.0 license.

NVIDIA and Mistral Artificial Intelligence partner to accelerate new family of open models

NVIDIA and Mistral Artificial Intelligence announced a partnership to optimize the Mistral 3 family of open-source multilingual, multimodal models across NVIDIA supercomputing and edge platforms. The collaboration highlights Mistral Large 3, a mixture-of-experts model designed to improve efficiency and accuracy for enterprise artificial intelligence deployments starting Tuesday, Dec. 2.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.