思想原子用于马尔可夫LLM测试时间扩展
Atom of Thoughts for Markov LLM Test-Time Scaling
AI总结：
本文提出思想原子（\our），通过马尔可夫链结构与树搜索等技术结合，实现高效推理，提升LLM测试时间扩展性能。
摘要：
大型语言模型（LLMs）通过测试时间扩展方法实现了显著的性能提升。然而，现有方法在推理过程中由于历史依赖信息的积累往往导致冗余计算。为了解决这一挑战，我们利用马尔可夫过程的记忆less性质，减少对历史上下文的依赖，并提出一种马尔可夫推理过程。这种基础的马尔可夫链结构能够无缝集成各种测试时间扩展方法，从而提高其扩展效率。通过进一步将马尔可夫推理链与树搜索和反思细化等技术相结合，我们揭示出一种涌现的原子推理结构，其中推理轨迹被分解为一系列自包含、低复杂度的原子单元。我们称这种设计为思想原子（\our）。大量实验表明，\our在计算预算增加时始终优于现有基线。重要的是，\our能够无缝集成现有推理框架和不同的LLM（包括推理和非推理LLM），从而实现可扩展的高性能推理。我们提交了本文的代码，并将公开发布以促进可重复性和未来研究。
英文摘要：
Large Language Models (LLMs) have achieved significant performance gains through test-time scaling methods. However, existing approaches often incur redundant computations due to the accumulation of historical dependency information during inference. To address this challenge, we leverage the memoryless property of Markov processes to minimize reliance on historical context and propose a Markovian reasoning process. This foundational Markov chain structure enables seamless integration with various test-time scaling methods, thereby improving their scaling efficiency. By further scaling up the Markovian reasoning chain through integration with techniques such as tree search and reflective refinement, we uncover an emergent atomic reasoning structure, where reasoning trajectories are decomposed into a series of self-contained, low-complexity atomic units. We name this design Atom of Thoughts (\our). Extensive experiments demonstrate that \our consistently outperforms existing baselines as computational budgets increase. Importantly, \our integrates seamlessly with existing reasoning frameworks and different LLMs (both reasoning and non-reasoning), facilitating scalable, high-performance inference.We submit our code alongside this paper and will make it publicly available to facilitate reproducibility and future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
