Zhengyao Jiang commited on
Commit
1eae860
·
unverified ·
1 Parent(s): d9a3340

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -6,7 +6,9 @@
6
  [![Discord](https://dcbadge.vercel.app/api/server/Rq7t8wnsuA?compact=true&style=flat)](https://discord.gg/Rq7t8wnsuA) 
7
  [![Twitter Follow](https://img.shields.io/twitter/follow/WecoAI?style=social)](https://twitter.com/WecoAI) 
8
 
9
- AIDE is an LLM agent that generates solutions for machine learning tasks just from natural language descriptions of the task. In a benchmark composed of over 60 Kaggle data science competitions, AIDE demonstrated impressive performance, surpassing 50% of Kaggle participants on average (see our [technical report](https://www.weco.ai/blog/technical-report) for details).
 
 
10
  More specifically, AIDE has the following features:
11
 
12
  1. **Instruct with Natural Language**: Describe your problem or additional requirements and expert insights, all in natural language.
 
6
  [![Discord](https://dcbadge.vercel.app/api/server/Rq7t8wnsuA?compact=true&style=flat)](https://discord.gg/Rq7t8wnsuA) 
7
  [![Twitter Follow](https://img.shields.io/twitter/follow/WecoAI?style=social)](https://twitter.com/WecoAI) 
8
 
9
+ AIDE is an LLM agent that generates solutions for machine learning tasks just from natural language descriptions of the task.
10
+ AIDE is the state-of-the-art agent on OpenAI's [MLE-bench](arxiv.org/pdf/2410.07095), a benchmark composed of 75 Kaggle machine learning tasks, where we achieved four times more medals compared to the runner-up agent architecture.
11
+ In our own benchmark composed of over 60 Kaggle data science competitions, AIDE demonstrated impressive performance, surpassing 50% of Kaggle participants on average (see our [technical report](https://www.weco.ai/blog/technical-report) for details).
12
  More specifically, AIDE has the following features:
13
 
14
  1. **Instruct with Natural Language**: Describe your problem or additional requirements and expert insights, all in natural language.