OS-Shepherd-35B-A3B

OS-Shepherd-35B-A3B

OS-Shepherd-35B-A3B is an open multimodal reward model for judging computer-use agent trajectories. Given a task instruction, screenshots, and the agent's reasoning and actions, it determines whether the task was completed and returns a reasoned SUCCESS or FAIL verdict.

It is fine-tuned from Qwen3.5-35B-A3B on OS-Shepherd-100K using the same SFT and GRPO recipe as OS-Shepherd-9B. The RL stage focuses on reducing false-success judgments.

Results

Results use the fixed judging protocol described in the OSReward paper.

Usage

Use the canonical prompt and trajectory format from the OSReward repository. A recent Transformers, vLLM, or SGLang version with Qwen3.5 multimodal support is required.

This model is intended for trajectory evaluation, data filtering, and reward-model research. It is not a computer-control policy and may still miss fine-grained visual failures, especially on hard cases.

License

Apache License 2.0. See LICENSE.

Citation

@article{sun2026osreward,
  title={OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models},
  author={Sun, Qiushi and others},
  journal={arXiv preprint arXiv:2607.28609},
  year={2026}
}