Fara-7B: An Efficient Agentic Model for Computer Use
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912727451041792 |
|---|---|
| author | Awadallah, Ahmed Lara, Yash Magazine, Raghav Mozannar, Hussein Nambi, Akshay Pandya, Yash Rajeswaran, Aravind Rosset, Corby Taymanov, Alexey Vineet, Vibhav Whitehead, Spencer Zhao, Andrew |
| author_facet | Awadallah, Ahmed Lara, Yash Magazine, Raghav Mozannar, Hussein Nambi, Akshay Pandya, Yash Rajeswaran, Aravind Rosset, Corby Taymanov, Alexey Vineet, Vibhav Whitehead, Spencer Zhao, Andrew |
| contents | Progress in computer use agents (CUAs) has been constrained by the absence of large and high-quality datasets that capture how humans interact with a computer. While LLMs have thrived on abundant textual data, no comparable corpus exists for CUA trajectories. To address these gaps, we introduce FaraGen, a novel synthetic data generation system for multi-step web tasks. FaraGen can propose diverse tasks from frequently used websites, generate multiple solution attempts, and filter successful trajectories using multiple verifiers. It achieves high throughput, yield, and diversity for multi-step web tasks, producing verified trajectories at approximately $1 each. We use this data to train Fara-7B, a native CUA model that perceives the computer using only screenshots, executes actions via predicted coordinates, and is small enough to run on-device. We find that Fara-7B outperforms other CUA models of comparable size on benchmarks like WebVoyager, Online-Mind2Web, and WebTailBench -- our novel benchmark that better captures under-represented web tasks in pre-existing benchmarks. Furthermore, Fara-7B is competitive with much larger frontier models, illustrating key benefits of scalable data generation systems in advancing small efficient agentic models. We are making Fara-7B open-weight on Microsoft Foundry and HuggingFace, and we are releasing WebTailBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19663 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fara-7B: An Efficient Agentic Model for Computer Use Awadallah, Ahmed Lara, Yash Magazine, Raghav Mozannar, Hussein Nambi, Akshay Pandya, Yash Rajeswaran, Aravind Rosset, Corby Taymanov, Alexey Vineet, Vibhav Whitehead, Spencer Zhao, Andrew Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Progress in computer use agents (CUAs) has been constrained by the absence of large and high-quality datasets that capture how humans interact with a computer. While LLMs have thrived on abundant textual data, no comparable corpus exists for CUA trajectories. To address these gaps, we introduce FaraGen, a novel synthetic data generation system for multi-step web tasks. FaraGen can propose diverse tasks from frequently used websites, generate multiple solution attempts, and filter successful trajectories using multiple verifiers. It achieves high throughput, yield, and diversity for multi-step web tasks, producing verified trajectories at approximately $1 each. We use this data to train Fara-7B, a native CUA model that perceives the computer using only screenshots, executes actions via predicted coordinates, and is small enough to run on-device. We find that Fara-7B outperforms other CUA models of comparable size on benchmarks like WebVoyager, Online-Mind2Web, and WebTailBench -- our novel benchmark that better captures under-represented web tasks in pre-existing benchmarks. Furthermore, Fara-7B is competitive with much larger frontier models, illustrating key benefits of scalable data generation systems in advancing small efficient agentic models. We are making Fara-7B open-weight on Microsoft Foundry and HuggingFace, and we are releasing WebTailBench. |
| title | Fara-7B: An Efficient Agentic Model for Computer Use |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.19663 |