TIGER-Lab/BrowserAgent-RFT

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Oct 17, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

TIGER-Lab/BrowserAgent-RFT is a 7.6 billion parameter model, initialized from Qwen/Qwen2.5-7B-Instruct, and further optimized for web browsing tasks. This model utilizes Reward Fine-Tuning (RFT) to enhance browsing trajectories, focusing on achieving higher success rates, shorter action paths, and safer interactions. It is specifically designed to function as a web agent, building upon human-inspired web browsing actions. With a context length of 131072 tokens, it is well-suited for complex, multi-step web automation and interaction scenarios.

Loading preview...

BrowserAgent-RFT: A Reward Fine-Tuned Web Agent

TIGER-Lab/BrowserAgent-RFT is a 7.6 billion parameter model developed by TIGER-Lab, building upon the Qwen/Qwen2.5-7B-Instruct base. Its core innovation lies in its Reward Fine-Tuning (RFT) approach, which optimizes web browsing trajectories using task-level reward signals.

Key Capabilities & Differentiators

  • Optimized Web Browsing: The model is specifically fine-tuned to perform web-based tasks more effectively by learning from reward signals.
  • Enhanced Trajectory Efficiency: RFT encourages the model to find shorter action paths to task completion, improving efficiency.
  • Higher Success Rates: The fine-tuning process aims to increase the overall success rate of web agent operations.
  • Safer Interactions: The model is designed to engage in safer interactions within web environments, minimizing unintended actions.
  • Human-Inspired Actions: BrowserAgent-RFT is built on the principles of human-inspired web browsing, making its actions more intuitive and effective for web automation.
  • Large Context Window: With a context length of 131072 tokens, it can handle extensive web page content and complex interaction histories.

Use Cases

This model is ideal for applications requiring intelligent web agents, such as:

  • Automated web navigation and data extraction.
  • Complex multi-step online task completion.
  • Developing agents that can interact with web interfaces in a human-like manner.

For more details, refer to the associated research paper: BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions.

Finetunes
1 models