EUVIMEDEUVIMED entdecken
Crossref

Hypothesis-Driven Reasoning for Large Language Models

Aakash Kumar Agarwal, Moyuru Yamada

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (3) · 1686-1693

DOI: 10.1609/aaai.v40i3.37146 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Aakash Kumar Agarwal und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper tackles the fundamental failure of Large Language Models (LLMs) to solve new tasks when prompted with a sufficient, yet overly complex, set of multi-modal episodes. This failure stems from the model's inability to distill underlying patterns from the noisy experiences. We propose Hypothesis-Driven Reasoning (HDR), a framework that enhances LLM reasoning by building an explicit semantic memory—a set of hypotheses induced from the multi-modal episodes. HDR employs a two-stage pipeline. It first extracts potential factors from the episodes and then iteratively refines hypotheses by generate-verify loop with the factors. We first empirically demonstrates this failure and the potential of sematic memory, showing that oracle hypotheses can boost accuracy from 35.3% to 92.0% on a novel task we designed. We then evaluate our HDR, achieving near-oracle performance and significantly outperforming baselines, especially on smaller models. This paper validates a shift from unstructured in-context recall to explicit knowledge abstraction for robust reasoning.

Zitieren

APA

Agarwal, A. K., & Yamada, M. (2026). Hypothesis-Driven Reasoning for Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(3), 1686-1693. https://doi.org/10.1609/aaai.v40i3.37146

Vancouver

Agarwal AK, Yamada M. Hypothesis-Driven Reasoning for Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(3):1686-1693. doi:10.1609/aaai.v40i3.37146

BibTeX
@article{Agarwal2026,
  author = {Agarwal, Aakash Kumar and Yamada, Moyuru},
  title = {Hypothesis-Driven Reasoning for Large Language Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {3},
  pages = {1686--1693},
  doi = {10.1609/aaai.v40i3.37146}
}
Kostenlos starten →