Language
Content
🚀 News • ✏️ Todo • ✨ Introduction
👀 Examples • 🎨 Quick Use • 🖥️ Environment
Links
Online Demo • Paper • Discord • Questionnaire
- [2025.03.18] Support two languages, English and Chinese.
- [2025.03.18] Support more LLM providers and models.
- [2025.03.18] Rate and provide comments in the questionnaire (takes about 30 seconds).
- [2025.03.17] Try the online demo through Huggingface Page!
- [2025.03.14] Join our Discord group!
- [2025.03.07] The paper is available in Arxiv.
- [2025.03.07] A new version has been uploaded.
- [2025.02.22] Create the Github page.
- Upload the demo vedio.
ReasonGraph is an open-source web platform for visualizing and analyzing reasoning processes of Large Language Models (LLMs).
- Model Support: Integrates with over 50 state-of-the-art models from major LLM providers including Anthropic, OpenAI, Google, Grok, Deepseek, Qwen, and Together.AI.
- Reasoning Methods: Implements mainstream reasoning approaches including sequential methods and tree-based methods.
- Modular Framework: Standardized APIs for easy integration of new reasoning methods and models.
- Beginner-Friendly: Intuitive UI design with visualization updates and simple configuration.
- Meta Reasoning: Built-in ability that allows models to self-select the most appropriate reasoning method.
Demo vedio:
UI Screenshot:
Visualisation of sequential reasoning methods:
Chain of Thoughts (top-left), Self-refine (top-middle), Least-to-most (top-right), Self-consistency (bottom-left):
Visualisation of tree-based reasoning methods:
Plain text (top), Beam Search (middle), Tree of Thoughts (bottom):
Try the online demo:
1. Go to the website: https://huggingface.co/spaces/ZongqianLi/ReasonGraph
Install the package:
<absolute_path>/ReasonGraph/
If you don't enter the API keys, the interface can still run normally, but you won't be able to use the corresponding models for inference.
<absolute_path>/ReasonGraph/api_keys.json
{
"anthropic": "<to be filled>",
"openai": "<to be filled>",
"google": "<to be filled>",
"together": "<to be filled>"
}
python app.py
* Running on all addresses (X.X.X.X)
* Running on http://XXX.X.X.X:XXXX
* Running on http://XX.XXX.XXX.XXX:XXXX
python==3.11.8
requests==2.31.0
openai==1.63.2
together==1.4.1
flask==3.1.0
google==3.0.0
google-genai==1.2.0
google-generativeai==0.8.4
@misc{li2025reasongraphvisualisationreasoningpaths,
title={ReasonGraph: Visualisation of Reasoning Paths},
author={Zongqian Li and Ehsan Shareghi and Nigel Collier},
year={2025},
eprint={2503.03979},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2503.03979},
}