Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908887893934080 |
|---|---|
| author | Peng, Huiyun Patil, Parth Vinod Qiu, Antonio Zhong Thiruvathukal, George K. Davis, James C. |
| author_facet | Peng, Huiyun Patil, Parth Vinod Qiu, Antonio Zhong Thiruvathukal, George K. Davis, James C. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14703 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization Peng, Huiyun Patil, Parth Vinod Qiu, Antonio Zhong Thiruvathukal, George K. Davis, James C. Software Engineering Artificial Intelligence 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. |
| title | Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2603.14703 |