EUVIMEDEUVIMED entdecken
Crossref

Multi-Step Reasoning with Large Language Models, a Survey

Aske Plaat, Annie Wong, Suzan Verberne, Joost Broekens, Niki Van Stein, Thomas Bäck

ACM Computing Surveys · 30.04.2026 · 58 (6) · 1-35

DOI: 10.1145/3774896 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 09.12.2025. Verfasst von Aske Plaat und 5 weiteren Autor:innen. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 198 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) with billions of parameters exhibit in-context learning abilities, enabling few-shot learning on tasks that the model was not specifically trained for. Traditional models achieve breakthrough performance on language tasks, but do not perform well on basic reasoning benchmarks. However, a new in-context learning approach, Chain-of-thought, has demonstrated strong multi-step reasoning abilities on these benchmarks. The research on LLM reasoning abilities started with the question whether LLMs can solve grade school math word problems, and has expanded to other tasks in the past few years. This article reviews the field of multi-step reasoning with LLMs. We propose a taxonomy that identifies different ways to generate, evaluate, and control multi-step reasoning. We provide an in-depth coverage of core approaches and open problems, and we propose a research agenda for the near future. We find that multi-step reasoning approaches have progressed beyond math word problems, and can now successfully solve challenges in logic, combinatorial games, and robotics, sometimes by first generating code that is then executed by external tools. Many studies in multi-step methods use reinforcement learning for finetuning, external optimization loops, in-context reinforcement learning, and self-reflection.

Zitieren

APA

Plaat, A., Wong, A., Verberne, S., Broekens, J., Stein, N. V., & Bäck, T. (2026). Multi-Step Reasoning with Large Language Models, a Survey. ACM Computing Surveys, 58(6), 1-35. https://doi.org/10.1145/3774896

Vancouver

Plaat A, Wong A, Verberne S, Broekens J, Stein NV, Bäck T. Multi-Step Reasoning with Large Language Models, a Survey. ACM Computing Surveys. 2026;58(6):1-35. doi:10.1145/3774896

BibTeX
@article{Plaat2026,
  author = {Plaat, Aske and Wong, Annie and Verberne, Suzan and Broekens, Joost and Stein, Niki Van and Bäck, Thomas},
  title = {Multi-Step Reasoning with Large Language Models, a Survey},
  journal = {ACM Computing Surveys},
  year = {2026},
  volume = {58},
  number = {6},
  pages = {1--35},
  doi = {10.1145/3774896}
}
Infokarte | EUVIMED

Artikeldaten derzeit nicht verfügbar.

Recherche