ReasonGraph: Visualisation of Reasoning Paths
This provides a tool for researchers and developers to reduce cognitive load and improve error detection in LLM reasoning processes, though it is incremental as it builds on existing visualization concepts for a specific domain.
The authors tackled the problem of analyzing complex reasoning processes in Large Language Models by developing ReasonGraph, a web-based visualization platform that supports sequential and tree-based reasoning methods with integration for over fifty state-of-the-art models. The evaluation demonstrated high parsing reliability, efficient processing, and strong usability across various applications.
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.