crab

项目介绍

CRAB is a framework for building LLM agent benchmark environments in a Python-centric way.

All datasets and experiment code are in crab-benchmark-v0 directory. Please carefully read the benchmark tutorial before using our benchmark.

Please cite our paper if you use anything related in your work:

Join us (Discord or WeChat) in pushing the boundaries of finding the scaling laws of agents.

[slack-url]: [slack-image]: [discord-url]: [discord-image]: [wechat-url]: [wechat-image]: [twitter-url]: [twitter-image]: [arxiv-image]: [arxiv-url]: