6
6
[ ![ Wechat] [ wechat-image ]] [ wechat-url ]
7
7
[ ![ Twitter] [ twitter-image ]] [ twitter-url ]
8
8
9
+ <p align =" center " >
10
+ <a href =" https://crab.camel-ai.org/ " >Website & Demos</a > |
11
+ <a href =" https://www.camel-ai.org/post/crab " >Blog</a > |
12
+ <a href =" https://dandansamax.github.io/posts/crab-paper/ " >Chinese Blog</a > |
13
+ <a href =" https://www.camel-ai.org/ " >CAMEL-AI</a >
14
+ </p >
15
+
16
+ <p align =" center " >
17
+ <img src =' https://raw.githubusercontent.com/camel-ai/crab/main/assets/CRAB_logo1.png ' width =800 >
18
+ </p >
19
+
9
20
## Overview
10
21
11
22
CRAB is a framework for building LLM agent benchmark environments in a Python-centric way.
@@ -18,10 +29,10 @@ CRAB is a framework for building LLM agent benchmark environments in a Python-ce
18
29
19
30
⚙ ️Easy-to-use Configuration
20
31
* Add a new action by simply adding a ` @action ` decorator on a Python function.
21
- * Deine the environment by integrating several actions together.
32
+ * Define the environment by integrating several actions together.
22
33
23
34
📐 Novel Benchmarking Suite
24
- * Define tasks and the corresponding evlauators in an intuitive Python-native way.
35
+ * Define tasks and the corresponding evaluators in an intuitive Python-native way.
25
36
* Introduce a novel graph evaluator method providing fine-grained metrics.
26
37
27
38
## Installation
@@ -72,4 +83,4 @@ Please cite [our paper](https://arxiv.org/abs/2407.01511) if you use anything re
72
83
[ twitter-url ] : https://twitter.com/CamelAIOrg
73
84
[ twitter-image ] : https://img.shields.io/twitter/follow/CamelAIOrg?style=social&color=brightgreen&logo=twitter
74
85
[ arxiv-image ] : https://img.shields.io/badge/arXiv-2407.01511-b31b1b.svg
75
- [ arxiv-url ] : https://arxiv.org/abs/2407.01511
86
+ [ arxiv-url ] : https://arxiv.org/abs/2407.01511
0 commit comments