---
title: README
emoji: ⚡
colorFrom: yellow
colorTo: green
sdk: static
pinned: false
---

## Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs

### Website: https://allenai.github.io/lumos/

### Paper: 

### Github: https://github.com/allenai/lumos

# 🪄 Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs
<p align="center">
  <a href="https://allenai.github.io/lumos/">
    <img src="https://img.shields.io/badge/🌐-Website-red">
  </a>
  <a href="">
    <img src="https://img.shields.io/badge/📝-Paper-blue">
  </a>
  <a href="https://huggingface.co/datasets?sort=trending&search=ai2lumos">
    <img src="https://img.shields.io/badge/🤗-Data-orange">
  </a>
  <a href="https://huggingface.co/models?sort=trending&search=ai2lumos">
    <img src="https://img.shields.io/badge/🤗-Model-green">
  </a> 
</p>

🖋 **Authors:** [Da Yin](https://wadeyin9712.github.io/), [Faeze Brahman](https://fabrahman.github.io/), [Abhilasha Ravichander](https://www.cs.cmu.edu/~aravicha/), [Khyathi Chandu](https://www.cs.cmu.edu/~kchandu/), [Kai-Wei Chang](http://web.cs.ucla.edu/~kwchang/), [Yejin Choi](https://homes.cs.washington.edu/~yejin/), [Bill Yuchen Lin](https://yuchenlin.xyz/)

We introduce 🪄**Lumos**, Language Agents with **Unified** Data Formats, **Modular** Design, and **Open-Source** LLMs. **Lumos** unifies a suite of complex interactive tasks and achieves competitive performance with GPT-4/3.5-based and larger open-source agents. 

‼️ **Lumos** has following features:
* 🧩 **Modular Architecture**:
  - **Lumos** consists of planning, grounding, and execution modules built based on LLAMA-2-7B.
* 🌍 **Diverse Training Data**:
  - **Lumos** is trained with ~40K high-quality annotations from ground-truth reasoning steps in existing benchmarks with GPT-4. 
* 🚀 **Competitive Performance**:
  - 🚀 **Lumos** outperforms **GPT-4/3.5-based** agents on complex QA and web tasks, and **larger open agents** on maths tasks.
  - 🚀 **Lumos** performs better than open agent baseline formulations including **chain-of-thoughts** and **integrated** training.
  - 🚀 **Lumos** surpasses larger open LLM agents and domain-specific agents on an unseen task, WebShop.
 
## 🤩 Citation

If you find this work is relevant with your research, please feel free to cite our work!
```
@article{yin2023lumos,
  title={Lumos: Language Agents with Unified Data Formats, Modular Design, and Open-Source LLMs},
  author={Yin, Da and Brahman, Faeze and Ravichander, Abhilasha and Chandu, Khyathi and Chang, Kai-Wei and Choi, Yejin and Lin, Bill Yuchen},
  year={2023}
}
```