OpenResearchAlpha

Intelligent Data Analysis: An International Journal · 12 Nov 2026

MAPS: Multi-armed bandit-guided adaptive prompt strategy selection for large language models

Yongquan Wan, Jiaxin Nan, Zijian Wang, Cairong Yanh-index 6

0
Citations
no database records one yet
0
Citations in 2026
so far
6
Leading author's h-index
Cairong Yan, in QAI's scholar index
6
References
works it cites, from open citation data

Citations by database

Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.

  • OpenCitations0
  • Crossref0

Citations per year

The current year is still counting.

  • 2026 so far0

Abstract

Prompt strategy selection plays a critical role in maximizing the effectiveness of Large Language Models (LLMs), yet existing prompt engineering methods typically rely on fixed strategies or heuristic rules, limiting their adaptability across diverse mathematical reasoning tasks. Although recent approaches introduce diverse prompting strategies, they lack a principled mechanism for dynamically selecting the most suitable strategy according to task characteristics and historical feedback. To address this challenge, we propose MAPS, a Multi-Armed bandit-guided Adaptive Prompt Strategy selection framework for LLMs. MAPS formulates prompt strategy selection as a sequential decision-making problem and employs Thompson Sampling to dynamically choose among candidate strategies based on observed LLM feedback. By leveraging the exploration-exploitation trade-off, MAPS continuously discovers potentially effective strategies while exploiting strategies with strong empirical performance. Furthermore, we formulate prompt strategy optimization through cumulative regret minimization and establish a sublinear regret bound, providing theoretical guarantees for efficient long-term learning in black-box LLM environments. Extensive experiments on four arithmetic reasoning benchmarks, including AddSub, GSM, MultiArith, and SingleEq, across multiple LLM backbones demonstrate that MAPS consistently outperforms individual prompt strategies, achieving an average accuracy improvement of 2.5%–6.8%. Moreover, MAPS reduces performance variance by 6.3%, indicating improved robustness and cross-model generalization on mathematical reasoning tasks. The source code is available at: https://anonymous.4open.science/r/MAPS-code-334D/

What the data shows

  • No database records a citation yet, as is usual for a paper this new.
  • Cairong Yan has the highest h-index among the authors (6).

Graph

This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.

Citing paper shares an authorAuthor without a profileSize shows citations, or h-index for authors

Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.

Start with

Authors (4)

Each author's standing in QAI's scholar index: the works their ORCID iD is attached to, and for anyone whose ORCID record names a lab OpenResearch follows, their arXiv preprints matched by name and a shared co-author. Names are as printed on the paper.

ProfileMost-cited paper

Cited by 0 papers

Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.

0 shown
No citing papers for this filter.

References (6)

What it cites, from open citation data, with Crossref's record of each.

PAL
Proceedings of the 13th ACM Conference on Recommender Systems · 2019
59
MAPS: Multi-armed bandit-guided adaptive prompt strategy selection for large language models - QAI OpenResearch