English

M$^3$Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation

Artificial Intelligence 2025-11-26 v1

Abstract

Recent advancements in multi-modal retrieval-augmented generation (mRAG), which enhance multi-modal large language models (MLLMs) with external knowledge, have demonstrated that the collective intelligence of multiple agents can significantly outperform a single model through effective communication. Despite impressive performance, existing multi-agent systems inherently incur substantial token overhead and increased computational costs, posing challenges for large-scale deployment. To address these issues, we propose a novel Multi-Modal Multi-agent hierarchical communication graph PRUNING framework, termed M3^3Prune. Our framework eliminates redundant edges across different modalities, achieving an optimal balance between task performance and token overhead. Specifically, M3^3Prune first applies intra-modal graph sparsification to textual and visual modalities, identifying the edges most critical for solving the task. Subsequently, we construct a dynamic communication topology using these key edges for inter-modal graph sparsification. Finally, we progressively prune redundant edges to obtain a more efficient and hierarchical topology. Extensive experiments on both general and domain-specific mRAG benchmarks demonstrate that our method consistently outperforms both single-agent and robust multi-agent mRAG systems while significantly reducing token consumption.

Keywords

Cite

@article{arxiv.2511.19969,
  title  = {M$^3$Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation},
  author = {Weizi Shao and Taolin Zhang and Zijie Zhou and Chen Chen and Chengyu Wang and Xiaofeng He},
  journal= {arXiv preprint arXiv:2511.19969},
  year   = {2025}
}
R2 v1 2026-07-01T07:53:39.576Z