|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- ai2lumos/lumos_web_agent_ground_iterative |
|
language: |
|
- en |
|
tags: |
|
- language-agent |
|
- web-agent |
|
- reasoning |
|
- grounding |
|
--- |
|
|
|
# 🪄 Agent Lumos: Unified and Modular Training for Open-Source Language Agents |
|
<p align="center"> |
|
🌐<a href="https://allenai.github.io/lumos">[Website]</a> |
|
📝<a href="https://arxiv.org/abs/2311.05657">[Paper]</a> |
|
🤗<a href="https://huggingface.co/datasets?sort=trending&search=ai2lumos">[Data]</a> |
|
🤗<a href="https://huggingface.co/models?sort=trending&search=ai2lumos">[Model]</a> |
|
🤗<a href="https://huggingface.co/spaces/ai2lumos/lumos_data_demo">[Demo]</a> |
|
</p> |
|
|
|
We introduce 🪄**Lumos**, Language Agents with **Unified** 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/13B and off-the-shelf APIs. |
|
- 🤗 **Lumos** utilizes a unified data format that encompasses multiple task types, thereby enabling the developed agent framework to conveniently support a range of interactive tasks. |
|
* 🌍 **Diverse Training Data**: |
|
- 🌍 **Lumos** is trained with ~56K diverse high-quality subgoal/action annotations from ground-truth reasoning steps in existing benchmarks with GPT-4. |
|
- ⚒️ **Lumos** data can be instrumental for future research in developing open-source agents for complex interactive tasks. |
|
* 🚀 **Competitive Performance**: |
|
- 🚀 **Lumos** is comparable or even beats **GPT-series** agents on web/complex QA tasks Mind2Web and HotpotQA, and **larger open agents** on math and multimodal tasks. |
|
- 🚀 **Lumos** exceeds contemporaneous agents that have been **fine-tuned** with in-domain HotpotQA, Mind2Web and ScienceQA annotations, such as **FiReAct**, **AgentLM**, and **AutoAct**. |
|
- 🚀 **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 unseen tasks, WebShop and InterCode_SQL. |
|
|
|
## Model Overview |
|
`lumos_web_agent_ground_iterative` is a **grounding** module checkpoint finetuned on **web agent** task in **Lumos-Iterative (Lumos-I)** formulation. |
|
|
|
The training annotation is shown below: |
|
|
|
| Training Data | Number | |
|
|---|---| |
|
|[`lumos_web_agent_ground_iterative`](https://huggingface.co/datasets/ai2lumos/lumos_web_agent_ground_iterative)|1009| |
|
|
|
|
|
## Citation |
|
|
|
If you find this work is relevant with your research, please feel free to cite our work! |
|
``` |
|
@article{yin2023lumos, |
|
title={Agent Lumos: Unified and Modular Training for Open-Source Language Agents}, |
|
author={Yin, Da and Brahman, Faeze and Ravichander, Abhilasha and Chandu, Khyathi and Chang, Kai-Wei and Choi, Yejin and Lin, Bill Yuchen}, |
|
journal={arXiv preprint arXiv:2311.05657}, |
|
year={2023} |
|
} |
|
``` |
