Create README.md

README.md

@@ -0,0 +1,89 @@
+---
+language:
+  - en
+license: other
+library_name: transformers
+pipeline_tag: image-text-to-text
+base_model: Qwen/Qwen3.5-9B
+datasets:
+  - AI45Research/SATraj-OS
+tags:
+  - computer-use-agent
+  - gui-agent
+  - multimodal
+  - supervised-fine-tuning
+  - safety
+  - osworld
+  - os-blind
+---
+
+# SCOPE-SFT-9B
+
+**SCOPE-SFT-9B** is a computer-use agent (CUA) trained under the SCOPE (Safety and Capability Optimization for Policy Execution) framework to balance task-execution capability with safety-aware decision-making. The model is initialized from **Qwen3.5-9B** and jointly fine-tuned on capability demonstrations, safe-continuation trajectories, and explicit-refusal trajectories.
+
+In our evaluation, SCOPE-SFT-9B achieves a **49.72%** task success rate on OSWorld and a **66.30%** attack-avoidance rate on OS-BLIND, corresponding to a capability-safety harmonic mean of **56.83%**.
+
+SCOPE-SFT-9B is trained on SATraj-OS using joint supervised fine-tuning. Capability demonstrations teach the model to complete benign desktop tasks, while safe-continuation and explicit-refusal trajectories teach it to respond appropriately when a request or execution environment presents a safety risk. SCOPE-SFT-9B also serves as the initialization checkpoint for SCOPE-RL-9B.
+
+## Links
+
+- Paper: [Beyond Task Completion: Training Capable and Safe Computer-Use Agents]()
+- Training dataset: [SATraj-OS](https://huggingface.co/datasets/AI45Research/SATraj-OS)
+- Data and safety framework: [Safactory](https://github.com/AI45Lab/SAfactory)
+- Model collection: [SCOPE](https://huggingface.co/collections/k4ng/scope)
+
+## Quick Start
+
+Install vLLM:
+
+```bash
+pip install -U vllm
+```
+
+Launch an OpenAI-compatible inference server:
+
+```bash
+vllm serve k4ng/SCOPE-SFT-9B \
+    --host 0.0.0.0 \
+    --port 8000 \
+    --tensor-parallel-size 1 \
+    --data-parallel-size 2 \
+    --trust-remote-code \
+    --served-model-name scope-sft
+```
+
+## Results
+
+| Type | Model | H ↑ | OSWorld ↑ | OS-BLIND ↑ |
+|---|---|---:|---:|---:|
+| Closed-source | Claude 4.5 Sonnet | 37.78 | 62.90 | 27.00 |
+| Closed-source | Qwen3.7-Plus | 9.36 | **73.33** | 5.00 |
+| Open-source | EvoCUA-8B | 10.62 | 46.06 | 6.00 |
+| Open-source | EvoCUA-32B | 4.42 | 56.73 | 2.30 |
+| Open-source | OpenCUA-7B | 3.21 | 28.85 | 1.70 |
+| Open-source | OpenCUA-32B | 1.94 | 34.79 | 1.00 |
+| Open-source | OpenCUA-72B | 4.38 | 44.99 | 2.30 |
+| Open-source | UI-TARS-1.5-7B | 8.46 | 27.52 | 5.00 |
+| Open-source | ComputerRL | 21.77 | 48.90 | 14.00 |
+| Open-source | Qwen3.5-9B | 8.93 | 41.80 | 5.00 |
+| Open-source | Qwen3-VL-8B | 16.27 | 33.90 | 10.70 |
+| SCOPE | **SCOPE-SFT-9B** | 56.83 | 49.72 | **66.30** |
+| SCOPE | SCOPE-RL-9B | **58.80** | **54.17** | 64.30 |
+
+All values are percentages, and ↑ indicates that higher is better. \(H\) is the harmonic mean of the OSWorld task success rate and the OS-BLIND attack-avoidance rate. Compared with the intermediate SFT checkpoint, SCOPE-SFT-9B improves OSWorld performance by 4.29 percentage points and attack avoidance by 13.97 points. The harmonic mean increases from 48.64% to 56.83%.
+
+## License
+
+This model is subject to the license terms of its base model, Qwen3.5-9B. Licensing information for the code and training data is available in the corresponding repositories.
+
+## Citation
+
+If you use SCOPE-RL, SCOPE-SFT, SATraj-OS, or SCOPE-Gen, please cite:
+
+```bibtex
+@misc{kang2026scope,
+  title  = {Beyond Task Completion: Training Capable and Safe Computer-Use Agents},
+  author = {Zeyu Kang and Zhenyun Yin and Yang Zhang and Shan He and Shanzhe Lei and Yanjiu Zhong and Xinquan Chen and Xuhong Wang},
+  year   = {2026}
+}
+```