xxwu

/

Agent-STAR-SFT-7B

like 0

Hi! I'm Niels, part of the community science team at Hugging Face.

This pull request improves the model card for this repository by:

• Adding a link to the corresponding research paper: Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe.
• Linking the official GitHub repository for the Agent-STAR project.
• Updating the metadata with the text-generation pipeline tag.
• Providing a model description explaining that this is the STAR-SFT-7B checkpoint trained on 1K trajectories.
• Including the BibTeX citation for researchers to reference the work.