ai2lumos/lumos_maths_plan_onetime

---
license: apache-2.0
task_categories:
- text-generation
language:
- en
tags:
- language-agent
- maths
- reasoning
size_categories:
- 10K<n<100K
---

# 🪄 Agent Lumos: Unified and Modular Training for Open-Source Language Agents
<p align="center">
🌐<a href="https://allenai.github.io/lumos">[Website]</a> &nbsp;
📝<a href="https://arxiv.org/abs/2311.05657">[Paper]</a> &nbsp;
🤗<a href="https://huggingface.co/datasets?sort=trending&search=ai2lumos">[Data]</a> &nbsp;
🤗<a href="https://huggingface.co/models?sort=trending&search=ai2lumos">[Model]</a> &nbsp;
🤗<a href="https://huggingface.co/spaces/ai2lumos/lumos_data_demo">[Demo]</a> &nbsp;
</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.

## Data Overview
`lumos_maths_plan_onetime` is the data for training **planning** module on **maths** task in **Lumos-Onetime (Lumos-O)** formulation.

The source of the training annotation training data is shown below:

| Task | Number |
|---|---|
|PRM800K|10000|
|GSM8K|7473|
|ASDiv|2305|

## Models Trained with the Data
`lumos_maths_plan_onetime` is used to train the following models.

|Model|Huggingface Repo|
|---|---|
|`lumos_maths_plan_onetime`| [🤗Huggingface Repo](https://huggingface.co/ai2lumos/lumos_maths_plan_onetime) |
|`lumos_maths_plan_onetime-13B`| [🤗Huggingface Repo](https://huggingface.co/ai2lumos/lumos_maths_plan_onetime-13B) |

## 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}
}
```

原始信息汇总

数据集概述

基本信息

• 许可证: Apache-2.0
• 任务类别: 文本生成
• 语言: 英语
• 标签: 语言代理, 数学, 推理
• 数据规模: 10K<n<100K

数据集详情

• 数据集名称: lumos_maths_plan_onetime
• 用途: 用于训练Lumos-Onetime (Lumos-O)框架中的数学任务的规划模块。

数据来源

任务	数量
PRM800K	10000
GSM8K	7473
ASDiv	2305

训练模型

• 模型名称: lumos_maths_plan_onetime

• Huggingface 仓库: 🤗Huggingface Repo

• 模型名称: lumos_maths_plan_onetime-13B

• Huggingface 仓库: 🤗Huggingface Repo