FireAct

Stats

⭐ Stars: 292

🍴 Forks: 21

📝 Language: Python

📅 Created: 2023-10-07

🔄 Updated: 2026-01-28

🏷️ Latest Release: No releases

Description

FireAct: Toward Language Agent Fine-tuning

Topics

agent, fine-tuning, large-language-models, llm, reasoning

Research Summary

Key Features

Architecture

Use Cases

Assessment

Maturity:

Documentation:

Community:

Recommendation:

README Excerpt

```

# FireAct: Toward Language Agent Fine-tuning


This repository is based on our publication *FireAct: Toward Language Agent Fine-tuning* ([PDF](https://browse.arxiv.org/pdf/2310.05915.pdf)). It contains prompts, demo code and fine-tuning data we generated. It also includes the description and directory for the model family we fine-tuned. If you use this code or data in your work, please cite:

```

@misc{chen2023fireact,

title={FireAct: Toward Language Agent Fine-tuning},

author={Baian Chen and Chang Shu and Ehsan Shareghi and Nigel Collier and Karthik Narasimhan and Shunyu Yao},

year={2023},

eprint={2310.05915},

archivePrefix={arXiv},

primaryClass={cs.CL}

}

```

Overview

Define tools in tools/

Define tasks in tasks/

Collect data & run experiments via generation.py

Results will be saved in trajs/

Data & Prompts

Data to generate training data and run experiments in data/. We also include samples of training data for both Alpaca format and GPT format. See details [here](https://github.com/anchen1011/FireAct/tree/main/data).

Prompts to generate training data and run experiments in prompts/

Setup

Set up OpenAI API key and store in environment variable (see [here](https://help.openai.com/en/articles/5112595-best-practices-for-api-key-safety))

```

export OPENAI_API_KEY=

```

Set up SERP API key and store in environment variable (see [here](https://serpapi.com))

```

export SERPAPI_API_KEY=

```

Create virtual env, for example with conda

```

conda create -n fireact python=3.9

conda activate fireact

```

Clone this repo and install dependencies

```

git clone https://github.com/anchen1011/FireAct.git

pip install -r requirements.txt

```

Run Demo

Data Generation

Example:

```

python generation.py \

--task hotpotqa \

--backend gpt-4 \

--promptpath default \

--evaluate \

--random \

--task_split val \

--temperature 0 \

--task_end_index 5

```

See details with command python generation.py -h

You need to set a high number (thousands) of --task_end_index to get sufficient good data samples. [WARNING] This is costly with gpt-4 and serpapi.

You need to convert trajectories into [alpaca format](https://github.com/tatsu-lab/stanford_alpaca#data-release) or [gpt format](https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset) for training. See our examples [here](https://github.com/anchen1011/FireAct/tree/main/data/finetune).

Supervised Fine-tuning

Example:

```

cd finetune/llama_lora

python finetune.py \

```

---

*Researched: 2026-03-27*