RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913986277015552 |
|---|---|
| author | Liu, Jun Kong, Zhenglun Yang, Changdi Yang, Fan Li, Tianqi Dong, Peiyan Nanjekye, Joannah Tang, Hao Yuan, Geng Niu, Wei Zhang, Wenbin Zhao, Pu Lin, Xue Huang, Dong Wang, Yanzhi |
| author_facet | Liu, Jun Kong, Zhenglun Yang, Changdi Yang, Fan Li, Tianqi Dong, Peiyan Nanjekye, Joannah Tang, Hao Yuan, Geng Niu, Wei Zhang, Wenbin Zhao, Pu Lin, Xue Huang, Dong Wang, Yanzhi |
| contents | Multi-agent large language model (LLM) systems have shown strong potential in complex reasoning and collaborative decision-making tasks. However, most existing coordination schemes rely on static or full-context routing strategies, which lead to excessive token consumption, redundant memory exposure, and limited adaptability across interaction rounds. We introduce RCR-Router, a modular and role-aware context routing framework designed to enable efficient, adaptive collaboration in multi-agent LLMs. To our knowledge, this is the first routing approach that dynamically selects semantically relevant memory subsets for each agent based on its role and task stage, while adhering to a strict token budget. A lightweight scoring policy guides memory selection, and agent outputs are iteratively integrated into a shared memory store to facilitate progressive context refinement. To better evaluate model behavior, we further propose an Answer Quality Score metric that captures LLM-generated explanations beyond standard QA accuracy. Experiments on three multi-hop QA benchmarks -- HotPotQA, MuSiQue, and 2WikiMultihop -- demonstrate that RCR-Router reduces token usage (up to 30%) while improving or maintaining answer quality. These results highlight the importance of structured memory routing and output-aware evaluation in advancing scalable multi-agent LLM systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04903 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory Liu, Jun Kong, Zhenglun Yang, Changdi Yang, Fan Li, Tianqi Dong, Peiyan Nanjekye, Joannah Tang, Hao Yuan, Geng Niu, Wei Zhang, Wenbin Zhao, Pu Lin, Xue Huang, Dong Wang, Yanzhi Computation and Language Artificial Intelligence Multiagent Systems Multi-agent large language model (LLM) systems have shown strong potential in complex reasoning and collaborative decision-making tasks. However, most existing coordination schemes rely on static or full-context routing strategies, which lead to excessive token consumption, redundant memory exposure, and limited adaptability across interaction rounds. We introduce RCR-Router, a modular and role-aware context routing framework designed to enable efficient, adaptive collaboration in multi-agent LLMs. To our knowledge, this is the first routing approach that dynamically selects semantically relevant memory subsets for each agent based on its role and task stage, while adhering to a strict token budget. A lightweight scoring policy guides memory selection, and agent outputs are iteratively integrated into a shared memory store to facilitate progressive context refinement. To better evaluate model behavior, we further propose an Answer Quality Score metric that captures LLM-generated explanations beyond standard QA accuracy. Experiments on three multi-hop QA benchmarks -- HotPotQA, MuSiQue, and 2WikiMultihop -- demonstrate that RCR-Router reduces token usage (up to 30%) while improving or maintaining answer quality. These results highlight the importance of structured memory routing and output-aware evaluation in advancing scalable multi-agent LLM systems. |
| title | RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory |
| topic | Computation and Language Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2508.04903 |