xxwu

/

Agent-STAR-RL-1.5B

like 0

Hi! I'm Niels from the community science team at Hugging Face.

This PR improves the model card for Agent-STAR-RL-1.5B. Key updates include:

• Adding relevant metadata (pipeline_tag, library_name, base_model).
• Linking the model to the original research paper: Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe.
• Providing a link to the official GitHub repository and related datasets.
• Including a sample inference usage snippet found in the GitHub documentation.
• Adding the BibTeX citation.