Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rahman, Asif, Cvetkovic, Veljko, Reece, Kathleen, Walters, Aidan, Hassan, Yasir, Tummeti, Aneesh, Torres, Bryan, Cooney, Denise, Ellis, Margaret, Nikolopoulos, Dimitrios S.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.03906
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915358032527360
author Rahman, Asif
Cvetkovic, Veljko
Reece, Kathleen
Walters, Aidan
Hassan, Yasir
Tummeti, Aneesh
Torres, Bryan
Cooney, Denise
Ellis, Margaret
Nikolopoulos, Dimitrios S.
author_facet Rahman, Asif
Cvetkovic, Veljko
Reece, Kathleen
Walters, Aidan
Hassan, Yasir
Tummeti, Aneesh
Torres, Bryan
Cooney, Denise
Ellis, Margaret
Nikolopoulos, Dimitrios S.
contents Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for parallelism, memory efficiency, and architecture-specific considerations that general-purpose LLMs often overlook. We present MARCO (Multi-Agent Reactive Code Optimizer), a novel framework that enhances LLM-generated code for HPC through a specialized multi-agent architecture. MARCO employs separate agents for code generation and performance evaluation, connected by a feedback loop that progressively refines optimizations. A key innovation is MARCO's web-search component that retrieves real-time optimization techniques from recent conference proceedings and research publications, bridging the knowledge gap in pre-trained LLMs. Our extensive evaluation on the LeetCode 75 problem set demonstrates that MARCO achieves a 14.6\% average runtime reduction compared to Claude 3.5 Sonnet alone, while the integration of the web-search component yields a 30.9\% performance improvement over the base MARCO system. These results highlight the potential of multi-agent systems to address the specialized requirements of high-performance code generation, offering a cost-effective alternative to domain-specific model fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03906
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing
Rahman, Asif
Cvetkovic, Veljko
Reece, Kathleen
Walters, Aidan
Hassan, Yasir
Tummeti, Aneesh
Torres, Bryan
Cooney, Denise
Ellis, Margaret
Nikolopoulos, Dimitrios S.
Distributed, Parallel, and Cluster Computing
Machine Learning
Software Engineering
Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for parallelism, memory efficiency, and architecture-specific considerations that general-purpose LLMs often overlook. We present MARCO (Multi-Agent Reactive Code Optimizer), a novel framework that enhances LLM-generated code for HPC through a specialized multi-agent architecture. MARCO employs separate agents for code generation and performance evaluation, connected by a feedback loop that progressively refines optimizations. A key innovation is MARCO's web-search component that retrieves real-time optimization techniques from recent conference proceedings and research publications, bridging the knowledge gap in pre-trained LLMs. Our extensive evaluation on the LeetCode 75 problem set demonstrates that MARCO achieves a 14.6\% average runtime reduction compared to Claude 3.5 Sonnet alone, while the integration of the web-search component yields a 30.9\% performance improvement over the base MARCO system. These results highlight the potential of multi-agent systems to address the specialized requirements of high-performance code generation, offering a cost-effective alternative to domain-specific model fine-tuning.
title MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing
topic Distributed, Parallel, and Cluster Computing
Machine Learning
Software Engineering
url https://arxiv.org/abs/2505.03906