RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory

TL;DR

RCR-Router is a novel role-aware context routing framework for multi-agent LLM systems that dynamically selects relevant memory subsets, reducing token consumption and enhancing answer quality in multi-hop question answering tasks.

Contribution

It introduces the first dynamic, role-aware memory routing approach that adapts context selection based on agent roles and task stages, improving efficiency and performance.

Findings

Reduces token usage by up to 30% in experiments.

Maintains or improves answer quality on multiple benchmarks.

Highlights the effectiveness of structured memory routing.

Abstract

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.