We are OS-Copilot Team from Shanghai AI Lab

🤩 Please check out our previous efforts on (multimodal) autonomous agents:

- [OS-Atlas](https://arxiv.org/abs/2410.23218) (Preprint) <br>
📘 OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

- [OS-Copilot](https://arxiv.org/abs/2402.07456) (Preprint) <br>
📘 OS-Copilot: Towards Generalist Computer Agents with Self-Improvement

- [SeeClick](https://arxiv.org/abs/2401.10935) (ACL'24) <br>
📘 SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

- [Symbol-LLM](https://arxiv.org/abs/2311.09278) (ACL'24) <br>
📘 Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models

- [ENVISIONS](https://arxiv.org/abs/2406.11736) (Preprint) <br>
📘 Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models

- [Corex](https://arxiv.org/abs/2310.00280) (COLM'24) <br>
📘 Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration