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

2026-03-13

AI Summary

This work addresses the challenges of high inference costs, latency, and limited interpretability in deployed multi-agent large language model (LLM) systems, where existing routing strategies struggle to achieve efficient, semantics-aware scheduling under dynamic workloads and mixed user intents. The authors propose AMRO-S, a novel framework that introduces ant colony optimization to multi-agent LLM routing for the first time. By integrating lightweight intent recognition, task-specific pheromone memory, and an asynchronous quality gating mechanism, AMRO-S enables low-overhead, highly transparent path selection. Experimental results across five public benchmarks and high-concurrency stress tests demonstrate consistent superiority over strong baselines, achieving improved trade-offs between output quality and computational cost. Moreover, the structured pheromone trails provide traceable, interpretable justifications for routing decisions.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Learning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• Multi-Agent Systems
• LLM Routing
• Interpretability
• Efficiency
• Semantic-aware Routing

Innovation

• Ant Colony Optimization
• Multi-Agent Routing
• Interpretable AI
• Semantic-aware Routing
• Quality-Cost Trade-off