license, library_name, pipeline_tag, base_model, tags

license	library_name	pipeline_tag	base_model	tags
mit	transformers	text-generation	Qwen/Qwen2.5-7B-Instruct	reinforcement-learning tool-use agent travel-planner

Agent-STAR-RL-7B

Agent-STAR-RL-7B is a 7B parameter model based on Qwen2.5-7B-Instruct, fine-tuned using Reinforcement Learning (RL) for long-horizon tool-use tasks.

This model is a key artifact of the paper Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe.

Model Description

The model was developed using the STAR [Data Synthesis → SFT → RL] pipeline, a unified post-training recipe for scaling RL in complex, multi-turn environments. It is specifically optimized for TravelPlanner, a challenging testbed requiring tool orchestration to satisfy multifaceted commonsense and hard constraints.

As per the systematic study in the paper, the 7B variant leverages GRPO (Group Relative Policy Optimization) with a dense SUM reward for optimized performance and faster convergence.

• Paper: Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
• Repository: https://github.com/WxxShirley/Agent-STAR
• Dataset: Agent-STAR-TravelDataset

Training Pipeline

1. Data Synthesis: Generation of synthetic queries and successful trajectories.
2. SFT: Fine-tuning from the backbone using ~1K successful trajectories.
3. RL: Scale-aware reinforcement learning tuning.

Usage

This model is designed to be used within a ReAct-style agentic framework. For reproducing the results on TravelPlanner, it is recommended to use the inference code provided in the official repository.

Inference Example

From the Agent-STAR repository root:

cd Inference
python3 -u main.py \
  --model xxwu/Agent-STAR-RL-7B \
  --save_suffix test_run \
  --max_workers 20 \
  --split validation \
  --max_context 32768 \
  --max_turns 60 

Citation

@misc{wu2026agentstar,
      title={Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe}, 
      author={Xixi Wu and Qianguo Sun and Ruiyang Zhang and Chao Song and Junlong Wu and Yiyan Qi and Hong Cheng},
      year={2026},
      eprint={2603.21972},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2603.21972}, 
}