TIGER-Lab/BrowserAgent-RFT
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...