Atom of Thoughts for Markov LLM Test-Time Scaling

Fengwei Teng, Quan Shi, Zhaoyang Yu, Jiayi Zhang, Yuyu Luo, Chenglin Wu, Zhijiang Guo

Keywords: LLM Reasoning, Reasoning Framework

TL;DR: The Atom of Thoughts leverages a Markovian reasoning process to enhance test-time scaling efficiency in LLMs, decomposing reasoning into low-complexity atomic units for scalable, high-performance inference.

Abstract:

Large Language Models (LLMs) achieve superior performance through training-time scaling, and test-time scaling further enhances their capabilities by conducting effective reasoning during inference.
However, as the scale of reasoning increases, existing test-time scaling methods suffer from accumulated historical information, which not only wastes computational resources but also interferes with effective reasoning.
To address this issue, we observe that complex reasoning can be achieved by solving a series of independent and self-contained subquestions. These subquestions are essentially \textit{atomic questions}, exhibiting the memoryless property similar to Markov processes.
Based on this observation, we propose Atom of Thoughts (\our), where each state transition consists of decomposing the current question into a dependency-based directed acyclic graph and contracting its subquestions, forming a simplified question that maintains answer equivalence with the original problem. This answer preservation enables the iterative \textit{decomposition-contraction} process to naturally form a meaningful Markov reasoning process.
Furthermore, these atomic states can be seamlessly integrated into existing test-time scaling methods, enabling \our to serve as a plug-in enhancement for improving reasoning capabilities.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 12226