Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.19969 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908673816657920 |
|---|---|
| author | Shao, Weizi Zhang, Taolin Zhou, Zijie Chen, Chen Wang, Chengyu He, Xiaofeng |
| author_facet | Shao, Weizi Zhang, Taolin Zhou, Zijie Chen, Chen Wang, Chengyu He, Xiaofeng |
| contents | 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 M$^3$Prune. Our framework eliminates redundant edges across different modalities, achieving an optimal balance between task performance and token overhead. Specifically, M$^3$Prune 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19969 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | M$^3$Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation Shao, Weizi Zhang, Taolin Zhou, Zijie Chen, Chen Wang, Chengyu He, Xiaofeng Artificial Intelligence 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 M$^3$Prune. Our framework eliminates redundant edges across different modalities, achieving an optimal balance between task performance and token overhead. Specifically, M$^3$Prune 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. |
| title | M$^3$Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2511.19969 |