Fara-7B: An Efficient Agentic Model for Computer Use

TL;DR

Fara-7B is a compact, efficient agentic model trained on a novel synthetic dataset, enabling it to perform multi-step web tasks effectively and outperform comparable models on new benchmarks.

Contribution

The paper introduces FaraGen, a synthetic data generation system, and Fara-7B, a small yet high-performing CUA model trained on this data, advancing web task automation.

Findings

Fara-7B outperforms similar-sized models on key benchmarks.

Fara-7B is competitive with larger models.

FaraGen produces diverse, high-quality web task trajectories.

Abstract

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.