Large Language Model Guided Tree-of-Thought

By Jieyi Long. arXiv.org, 2023

335 citations recorded by the source corpus.

In this paper, we introduce the Tree-of-Thought (ToT) framework, a novel approach aimed at improving the problem-solving capabilities of auto-regressive large language models (LLMs). The ToT technique is inspired by the human mind's approach for solving complex reasoning tasks through trial and error. In this process, the human mind explores the solution space through a tree-like thought process, allowing for backtracking when necessary. To implement ToT as a software system, we augment an LLM with additional modules including a prompter agent, a checker module, a memory module, and a ToT controller. In order to solve a given problem, these modules engage in a multi-round conversation with the LLM. The memory module records the conversation and state history of the problem solving process, which allows the system to backtrack to the previous steps of the thought-process and explore other directions from there. To verify the effectiveness of the proposed technique, we implemented a ToT-based solver for the Sudoku Puzzle. Experimental results show that the ToT framework can significantly increase the success rate of Sudoku puzzle solving. Our implementation of the ToT-based Sudoku solver is available on GitHub: \url{https://github.com/jieyilong/tree-of-thought-puzzle-solver}.

Subfields: Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/bda605928d6ebe4db906e69ab5d343df75918727

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

Citations in the corpus

Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training (2023, neutral): “Preliminary work in this field includes Tree-of-Thought (ToT) (Yao et al., 2023; Long, 2023) with depth/breadth-first search and Reasoning-via-Planing (RAP)(Hao et al., 2023) with MCTS.”
WebArena: A Realistic Web Environment for Building Autonomous Agents (2023, methodology): “Meanwhile, search and backtracking methods introduce a more structured approach to planning while also allowing for decision reconsideration (Yao et al., 2023; Long, 2023).”
Graph of Thoughts: Solving Elaborate Problems with Large Language Models (2023, methodology): “Chain-of-Thought (CoT) [70] é é é Self-Consistency with CoT [66] é é Thought decomposition [74] é Tree-of-Thought (ToT) [43] é Tree of Thoughts (ToT) [76] é”
Autonomous chemical research with large language models (2023, positive): “This can be done through advanced prompting strategies, such as ReAct 34 , Chain of Thought 35 and Tree of Thoughts 36 .”
A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications (2024, positive): “Tree-of-Thoughts (ToT) Prompting Yao et al. [2023a] and Long [2023] proposed the Tree-of-Thoughts (ToT) framework to enhance prompting capabilities for complex tasks requiring exploration and look-ahead reasoning.”
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model (2024, background): “Consequently, there have been numerous extensions and revisions works on CoT such as multi-sampling, tree-of-thoughts (Long, 2023), graph-of-thoughts (Yao et al., 2023), algorithm-of-thoughts (Sel et al., 2023), and automatic CoT construction (Kojima et al., 2022; Xu et al., 2023b).”
Evaluating Large Language Models in Class-Level Code Generation (2024, positive): “While researchers have proposeddiversepromptingstrategiessuchaschain-of-thought[29] andtree-of-thought[48]toimprovemodelperformanceinsolving complicatedtasks,andthisworkalsomakessomeinitialexplo-rationsonthreegenerationstrategiesforclass-levelcodingtasks,…”
Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review (2023, background): “Another research by [64], further emphasized the potential of this technique in enhancing the performance of LLMs by structuring their thought processes.”