Graph of Thoughts (GoT)
First page
Paper summary
Generalizes Chain-of-Thought and Tree-of-Thought by modeling LLM reasoning as an arbitrary graph.
Ask this paper
01
Arbitrary graph structure: Represents LLM-generated thoughts as nodes in a graph with arbitrary edges - allowing merging, looping, and non-tree structures.
02
Feedback loops: Enables explicit feedback loops where earlier thoughts can be revised based on later exploration - impossible in strictly linear or tree-structured reasoning.
03
Network reasoning: The authors call this "network reasoning", treating reasoning as a graph-exploration problem rather than a linear or branching one.
04
No model updates: Like CoT and ToT, works purely at prompting level without any model fine-tuning - extending the chain-of-X prompting family.