Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation
Abstract
A framework for adaptive selection and dynamic weighted fusion of knowledge from multiple LLMs reduces interference and improves scalability in knowledge aggregation.
Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble and weight merging require substantial memory and struggle to adapt to changing data environments. Recent efforts have transferred knowledge from multiple LLMs into a single target model; however, they suffer from interference and degraded performance among tasks, largely due to limited flexibility in candidate selection and training pipelines. To address these issues, we propose a framework that adaptively selects and aggregates knowledge from diverse LLMs to build a single, stronger model, avoiding the high memory overhead of ensemble and inflexible weight merging. Specifically, we design an adaptive selection network that identifies the most relevant source LLMs based on their scores, thereby reducing knowledge interference. We further propose a dynamic weighted fusion strategy that accounts for the inherent strengths of candidate LLMs, along with a feedback-driven loss function that prevents the selector from converging on a single subset of sources. Experimental results demonstrate that our method can enable a more stable and scalable knowledge aggregation process while reducing knowledge interference by up to 50% compared to existing approaches. Code is avaliable at https://github.com/ZLKong/LLM_Integration
Community
The contributions are as follows:
• The paper finds that merely increasing the number of fusion candidates and expanding the source model pool does not necessarily enhance the fusion process, a selective strategy is more effective in
minimizing knowledge interference.
• The paper proposes a novel dynamic integration framework that adaptively selects LLMs for integration, leveraging an adaptive selection network, a dynamic weighted fusion strategy, and a feedback-driven loss function to alleviate interference issues and enhance performance.
• The model shows improvement in accuracy across multiple benchmarks as more models are
integrated, while reducing knowledge interference by up to 50% compared to previous methods.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models (2025)
- Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2025)
- Knowledge Grafting of Large Language Models (2025)
- MergeBench: A Benchmark for Merging Domain-Specialized LLMs (2025)
- Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging (2025)
- LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead (2025)
- SeMe: Training-Free Language Model Merging via Semantic Alignment (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper