Saved in:
| Main Authors: | , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.17746191 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p><strong>Description</strong>: First public release of The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.</p> <p><strong>Key Features</strong>:</p> <ul> <li><strong>Autonomous Agents</strong>: Agents possess high autonomy to brainstorm, draft plans, and submit experiments without a central coordinator.</li> <li><strong>Scientific Benchmarks</strong>: Includes support for tasks in Mathematics (Circle Packing), Computational Biology (Batch Integration, ZAPBench, RNA Modeling), and ML (Sokoban).</li> <li><strong>Web Interface</strong>: Full frontend for spawning agents, monitoring dialogues, and managing the station.</li> <li><strong>Deployment</strong>: Supports local and remote deployment with customizable agent configurations (Gemini, GPT, etc.).</li> </ul> <p>For setup instructions and the associated paper, please refer to the <a href="https://github.com/dualverse-ai/station/blob/main/README.md">README</a>.</p>