graph-of-thoughts and Algorithm-Of-Thoughts
These are competing approaches to structured LLM reasoning that both augment chain-of-thought prompting with graph-based exploration of solution spaces, but Graph of Thoughts uses explicit graph construction while Algorithm of Thoughts uses tree-based thought branching.
About graph-of-thoughts
spcl/graph-of-thoughts
Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"
Constructs problem-solving workflows as directed acyclic graphs of LLM operations (Generate, Score, Aggregate, etc.), enabling flexible composition of reasoning strategies from simple Chain-of-Thought to more sophisticated multi-path exploration. Supports pluggable LLM backends (ChatGPT, local models via controller abstraction) and includes custom prompters/parsers for domain-specific problems. Provides built-in examples for sorting and keyword counting that demonstrate how to define scoring functions and ground-truth validation within the operation graph.
About Algorithm-Of-Thoughts
kyegomez/Algorithm-Of-Thoughts
My implementation of "Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models"
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work