# Efficient Dynamic Ensembling for Multiple LLM Experts

arXiv: https://arxiv.org/abs/2412.07448 · HTML: https://mlsanity.com/paper/2412.07448/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought](https://mlsanity.com/paper/2305.15021/) (2023)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models](https://mlsanity.com/paper/2311.08692/) (2023)
- [Knowledge Fusion of Large Language Models](https://mlsanity.com/paper/2401.10491/) (2024)
- [Merging Multi-Task Models via Weight-Ensembling Mixture of Experts](https://mlsanity.com/paper/2402.00433/) (2024)
- [Solving Math Word Problem with Problem Type Classification](https://mlsanity.com/paper/2308.13844/) (2023)
- [Dobby: A Conversational Service Robot Driven by GPT-4](https://mlsanity.com/paper/2310.06303/) (2023)

## Built on by (most cited first, 9 of 9)

- [Test-Time Learning for Large Language Models](https://mlsanity.com/paper/2505.20633/) (2025)
- [Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems](https://mlsanity.com/paper/2502.00409/) (2025)
- [C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning](https://mlsanity.com/paper/2511.07396/) (2025)
- [Dynamic Compressing Prompts for Efficient Inference of Large Language Models](https://mlsanity.com/paper/2504.11004/) (2025)
- [Continual Knowledge Adaptation for Reinforcement Learning](https://mlsanity.com/paper/2510.19314/) (2025)
- [Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance](https://mlsanity.com/paper/2505.12334/) (2025)
- [Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models](https://mlsanity.com/paper/2512.15089/) (2025)
- [Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation](https://mlsanity.com/paper/2607.27783/) (2026)
- [WattCouncil: Context-Aware Household Energy Scenario Generation With Governed LLMs](https://mlsanity.com/paper/2607.10720/) (2026)

## Abstract (arXiv)

LLMs have demonstrated impressive performance across various language tasks. However, the strengths of LLMs can vary due to different architectures, model sizes, areas of training data, etc. Therefore, ensemble reasoning for the strengths of different LLM experts is critical to achieving consistent and satisfactory performance on diverse inputs across a wide range of tasks. However, existing LLM ensemble methods are either computationally intensive or incapable of leveraging complementary knowledge among LLM experts for various inputs. In this paper, we propose an efficient Dynamic Ensemble Reasoning paradigm, called DER to integrate the strengths of multiple LLM experts conditioned on dynamic inputs. Specifically, we model the LLM ensemble reasoning problem as a Markov Decision Process, wherein an agent sequentially takes inputs to request knowledge from an LLM candidate and passes the output to a subsequent LLM candidate. Moreover, we devise a reward function to train a DER-Agent to dynamically select an optimal answering route given the input questions, aiming to achieve the highest performance with as few computational resources as possible. Last, to fully transfer the expert knowledge from the prior LLMs, we develop a Knowledge Transfer Prompt that enables the subsequent LLM candidates to transfer complementary knowledge effectively. Experiments demonstrate that our method uses fewer computational resources to achieve better performance compared to state-of-the-art baselines. Code and appendix are available at https://github.com/Fhujinwu/DER