arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16512cs.AI
收藏

思维框架:基于链、树和图的动态优化推理基础框架

Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs

School of Computation, Information and Technology(计算、信息与技术学院);Technical University of Munich(慕尼黑技术大学)

Felix Fricke, Simon Malberg, Georg Groh

AI总结:

研究针对现有思维提示方案的局限,提出通用基础框架FoT,内置超参调整等功能,通过在其中实现三种流行方案验证其能力,能加快执行、降低成本并获更好任务分数,还发布代码库促进相关推理方案发展。

摘要:

诸如思维链、思维树和思维图等提示方案可显著增强大语言模型的推理能力。然而,大多数现有方案要求用户定义静态、特定问题的推理结构,缺乏对动态或未知问题类型的适应性。此外,这些方案在超参数、提示、运行时和提示成本方面往往未得到充分优化。为解决这些限制,我们引入了思维框架(FoT)——一个用于构建和优化动态推理方案的通用基础框架。FoT具有超参数调整、提示优化、并行执行和智能缓存等内置功能,释放了推理方案的潜在性能潜力。我们通过在FoT中实现三种流行方案——思维树、思维图和概率树——来展示FoT的能力。我们通过实验表明,FoT能够显著加快执行速度、降低成本,并通过优化获得更好的任务分数。我们发布了我们的代码库,以促进未来动态高效推理方案的开发。

英文摘要:

Prompting schemes such as Chain of Thought, Tree of Thoughts, and Graph of Thoughts can significantly enhance the reasoning capabilities of large language models. However, most existing schemes require users to define static, problem-specific reasoning structures that lack adaptability to dynamic or unseen problem types. Additionally, these schemes are often under-optimized in terms of hyperparameters, prompts, runtime, and prompting cost. To address these limitations, we introduce Framework of Thoughts (FoT)--a general-purpose foundation framework for building and optimizing dynamic reasoning schemes. FoT comes with built-in features for hyperparameter tuning, prompt optimization, parallel execution, and intelligent caching, unlocking the latent performance potential of reasoning schemes. We demonstrate FoT's capabilities by implementing three popular schemes--Tree of Thoughts, Graph of Thoughts, and ProbTree--within FoT. We empirically show that FoT enables significantly faster execution, reduces costs, and achieves better task scores through optimization. We release our codebase to facilitate the development of future dynamic and efficient reasoning schemes.

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。

↑