seta-rl-qwen3-8b

SETA RL finetuned model

<p align="center"> <img src="assets/TerminalAgent.jpg" width="90%"> </p> <p align="center"> <a href="https://github.com/camel-ai/seta" style="margin-right: 24px; margin-left: 24px;">SETA Code</a> | <a href="https://github.com/camel-ai/seta-env/tree/main/Dataset" style="margin-right: 24px; margin-left: 24px;">RL dataset</a> | <a href="https://eigent-ai.notion.site/SETA-Scaling-Environments-for-Terminal-Agents-2d2511c70ba280a9b7c0fe3e7f1b6ab8" style="margin-right: 24px; margin-left: 24px;">Project Report</a> | <a href="https://huggingface.co/camel-ai/seta-rl-qwen3-8b" style="margin-left: 24px;">RL model</a> </p>

Model Description

SETA is part of CAMEL-AI Scaling Environments for Agents project, aimed at producing scalable Terminal Environments for RL training.

Usage

1. Clone the code repo

git clone https://github.com/camel-ai/seta

1. Set the path in config file

checkout example script Config file

Links

• 🌐 SETA Github
• 💻 SETA RL Repo
• 🧠 CAMEL Github
• 🧠 SETA RL model
• 🧠 Technical Report (‼️Continuous updates)

Citation

@misc{seta,
  author = {Qijia Shen, Jay Rainton, Aznaur Aliev, Ahmed Awelkair, Boyuan Ma, Zhiqi (Julie) Huang, Yuzhen Mao, Wendong Fan, Philip Torr, Bernard Ghanem, Changran Hu, Urmish Thakker, Guohao Li},
  month = Jan,
  title = {{SETA: Scaling Environments for Terminal Agents}},
  year = {2026}
}

Refer to SETA Repo for Agents and RL training.