Algorithmic Thinking Theory

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bateni, MohammadHossein, Cohen-Addad, Vincent, Gu, Yuzhou, Lattanzi, Silvio, Meierhans, Simon, Mohri, Christopher
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911302141607936
author Bateni, MohammadHossein
Cohen-Addad, Vincent
Gu, Yuzhou
Lattanzi, Silvio
Meierhans, Simon
Mohri, Christopher
author_facet Bateni, MohammadHossein
Cohen-Addad, Vincent
Gu, Yuzhou
Lattanzi, Silvio
Meierhans, Simon
Mohri, Christopher
contents Large language models (LLMs) have proven to be highly effective for solving complex reasoning tasks. Surprisingly, their capabilities can often be improved by iterating on previously generated solutions. In this context, a reasoning plan for generating and combining a set of solutions can be thought of as an algorithm for reasoning using a probabilistic oracle. We introduce a theoretical framework for analyzing such reasoning algorithms. This framework formalizes the principles underlying popular techniques for iterative improvement and answer aggregation, providing a foundation for designing a new generation of more powerful reasoning methods. Unlike approaches for understanding models that rely on architectural specifics, our model is grounded in experimental evidence. As a result, it offers a general perspective that may extend to a wide range of current and future reasoning oracles.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Algorithmic Thinking Theory
Bateni, MohammadHossein
Cohen-Addad, Vincent
Gu, Yuzhou
Lattanzi, Silvio
Meierhans, Simon
Mohri, Christopher
Artificial Intelligence
Computation and Language
Large language models (LLMs) have proven to be highly effective for solving complex reasoning tasks. Surprisingly, their capabilities can often be improved by iterating on previously generated solutions. In this context, a reasoning plan for generating and combining a set of solutions can be thought of as an algorithm for reasoning using a probabilistic oracle. We introduce a theoretical framework for analyzing such reasoning algorithms. This framework formalizes the principles underlying popular techniques for iterative improvement and answer aggregation, providing a foundation for designing a new generation of more powerful reasoning methods. Unlike approaches for understanding models that rely on architectural specifics, our model is grounded in experimental evidence. As a result, it offers a general perspective that may extend to a wide range of current and future reasoning oracles.
title Algorithmic Thinking Theory
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2512.04923