---
title: "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble"
authors:
  - "Zhijun Chen"
  - "Xiaodong Lu"
  - "Jingzheng Li"
  - "Pengpeng Chen"
  - "Zhuoran Li"
  - "Kai Sun"
  - "Yuankai Luo"
  - "Qianren Mao"
  - "Ming Li"
  - "Likang Xiao"
  - "Dingqi Yang"
  - "Yikun Ban"
  - "Hailong Sun"
doi: "10.24963/ijcai.2026/867"
url: "https://ijcai.org/proceedings/2026/867"
pdf: "https://ijcai.org/proceedings/2026/0867.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "7807-7816"
track: "Survey Track"
keywords:
  - "Agent-based and Multi-agent Systems: Other"
  - "SV: Agent-based and Multi-agent Systems"
  - "Machine Learning: Ensemble methods"
  - "Natural Language Processing: Applications"
---

# Harnessing Multiple Large Language Models: A Survey on LLM Ensemble

Zhijun Chen, Xiaodong Lu, Jingzheng Li, Pengpeng Chen, Zhuoran Li, Kai Sun, Yuankai Luo, Qianren Mao, Ming Li, Likang Xiao, Dingqi Yang, Yikun Ban, Hailong Sun

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 7807-7816. DOI: [10.24963/ijcai.2026/867](https://doi.org/10.24963/ijcai.2026/867)

## Abstract

LLM Ensemble---which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths---has gained substantial attention recently. The widespread availability of LLMs, coupled with their varying strengths and out-of-the-box usability, has profoundly advanced the field of LLM Ensemble. This paper presents the first systematic review of recent developments in LLM Ensemble. First, we introduce our taxonomy of LLM Ensemble and discuss several related research problems. Then, we provide a more in-depth classification of the methods under the broad categories of ``ensemble-before-inference, ensemble-during-inference, ensemble-after-inference'', and review relevant methods. Finally, we introduce related benchmarks and applications, summarize existing studies, and suggest  future research directions. GitHub project link is: https://github.com/junchenzhi/Awesome-LLM-Ensemble.