Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization

2026-03-15

AI Summary

This work addresses the limitations of existing AI-driven code optimization approaches, which are often confined to local syntactic transformations and struggle to model cross-component performance interactions and architectural-level effects in modern systems such as microservices. To overcome this, the paper proposes a multi-agent collaborative reasoning framework that integrates control flow, data flow, and system architecture dependencies through four specialized agent roles—summarization, analysis, optimization, and validation—to enable whole-system performance optimization. This approach represents the first application of a multi-agent mechanism to system-level software optimization, facilitating the generation of global, multi-step strategies across components. Evaluated on a microservices prototype, the method achieves a 36.58% improvement in throughput and a 27.81% reduction in average response time.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Search and Optimization: Metareasoning and Metaheuristics
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Large language models and AI agents have recently shown promise in automating software performance optimization, but existing approaches predominantly rely on local, syntax-driven code transformations. This limits their ability to reason about program behavior and capture whole system performance interactions. As modern software increasingly comprises interacting components - such as microservices, databases, and shared infrastructure - effective code optimization requires reasoning about program structure and system architecture beyond individual functions or files. This paper explores the feasibility of whole system optimization for microservices. We introduce a multi-agent framework that integrates control-flow and data-flow representations with architectural and cross-component dependency signals to support system-level performance reasoning. The proposed system is decomposed into coordinated agent roles - summarization, analysis, optimization, and verification - that collaboratively identify cross-cutting bottlenecks and construct multi-step optimization strategies spanning the software stack. We present a proof-of-concept on a microservice-based system that illustrates the effectiveness of our proposed framework, achieving a 36.58% improvement in throughput and a 27.81% reduction in average response time.

Problem

• software system optimization
• multi-agent reasoning
• whole system performance
• microservices
• cross-component dependencies

Innovation

• multi-agent reasoning
• whole system optimization
• microservices
• cross-component dependency
• performance optimization