RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
This addresses scalability and efficiency issues for developers of multi-agent LLM systems, though it is incremental as it builds on existing routing strategies with a novel dynamic approach.
The paper tackled the problem of inefficient context routing in multi-agent LLM systems, which causes high token usage and redundant memory exposure, by introducing RCR-Router, a role-aware routing framework that reduced token usage by up to 30% while maintaining or improving answer quality on multi-hop QA benchmarks.
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.