Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization

TL;DR

This paper introduces AMRO-S, an efficient, interpretable routing framework for multi-agent systems that improves performance and resource utilization by combining semantic intent inference, task-specific memory, and asynchronous updates.

Contribution

AMRO-S is a novel routing approach that models semantic-aware path selection with low overhead, task-specific memory, and decoupled inference and learning, addressing limitations of existing methods.

Findings

Consistently outperforms baseline routing strategies in quality-cost trade-off.

Reduces inference latency through small language model intent inference.

Provides traceable routing evidence via structured pheromone patterns.

Abstract

Large Language Model (LLM)-driven Multi-Agent Systems (MAS) have demonstrated strong capability in complex reasoning and tool use, and heterogeneous agent pools further broaden the quality--cost trade-off space. Despite these advances, real-world deployment is often constrained by high inference cost, latency, and limited transparency, which hinders scalable and efficient routing. Existing routing strategies typically rely on expensive LLM-based selectors or static policies, and offer limited controllability for semantic-aware routing under dynamic loads and mixed intents, often resulting in unstable performance and inefficient resource utilization. To address these limitations, we propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS). AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms: First, it leverages a supervised fine-tuned (SFT) small language model for intent inference, providing a low-overhead semantic interface for each query; second, it decomposes routing memory into task-specific pheromone specialists, reducing cross-task interference and optimizing path selection under mixed workloads; finally, it employs a quality-gated asynchronous update mechanism to decouple inference from learning, optimizing routing without increasing latency. Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines, while providing traceable routing evidence through structured pheromone patterns.