可视化大模型推理路径，帮助理解复杂思维过程。
ReasonGraph: Visualisation of Reasoning Paths
- 构建网页平台，支持串行与树状推理路径的图形化展示。
- 可对接50+主流大模型，解析准确率高、处理效率快。
- 适合研究者与开发者调试模型逻辑，提升可解释性。
大型语言模型（LLMs）的推理过程因复杂性高且缺乏结构化可视化工具而难以分析。我们提出ReasonGraph，一个基于网页的平台，用于可视化和分析LLM的推理过程。该平台支持序列式与树状推理方法，兼容主流LLM提供商及超过五十个先进模型。ReasonGraph具备直观的用户界面，支持元推理方法选择、可配置的可视化参数，并采用模块化框架以实现高效扩展。评估表明，其具有高解析可靠性、高效处理能力以及强可用性，适用于多种下游应用。通过提供统一的可视化框架，ReasonGraph降低了分析复杂推理路径的认知负担，提升了逻辑错误检测能力，推动了基于LLM应用的有效开发。平台开源，促进可复现性与可访问性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) reasoning processes are challenging to analyze due to their complexity and the lack of organized visualization tools. We present ReasonGraph, a web-based platform for visualizing and analyzing LLM reasoning processes. It supports both sequential and tree-based reasoning methods while integrating with major LLM providers and over fifty state-of-the-art models. ReasonGraph incorporates an intuitive UI with meta reasoning method selection, configurable visualization parameters, and a modular framework that facilitates efficient extension. Our evaluation shows high parsing reliability, efficient processing, and strong usability across various downstream applications. By providing a unified visualization framework, ReasonGraph reduces cognitive load in analyzing complex reasoning paths, improves error detection in logical processes, and enables more effective development of LLM-based applications. The platform is open-source, promoting accessibility and reproducibility in LLM reasoning analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。