paper-with-me

Papers

MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing

2025-05-06 · Asif Rahman, Veljko Cvetkovic, Kathleen Reece, Aidan Walters, Yasir Hassan, Aneesh Tummeti, Bryan Torres, Denise Cooney, Margaret Ellis, Dimitrios S. Nikolopoulos

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.

📄 PDF Abstract BibTeX arXiv:2505.03906

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Methods 이 논문이 사용한 방법론

BASE 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

MARCO: Multi-Agent Real-time Chat Orchestration

2024-10-29 · Anubhav Shrimal, Stanley Kanagaraj, Kriti Biswas, Swarnalatha Raghuraman 외

Large language model advancements have enabled the development of multi-agent frameworks to tackle complex, real-world problems such as to automate tasks that require interactions with diverse tools, reasoning, and human…

HallucinationLanguage ModelingLanguage ModellingLarge Language Model

MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering

2025-06-16 · Arya Fayyazi, Mehdi Kamal, Massoud Pedram

This paper introduces MARCO (Multi-Agent Reinforcement learning with Conformal Optimization), a novel hardware-aware framework for efficient neural architecture search (NAS) targeting resource-constrained edge devices. B…

Conformal PredictionHardware Aware Neural Architecture SearchMulti-agent Reinforcement LearningNeural Architecture Search

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

2026-03-30 · Bin Zhu, Qianghuai Jia, Tian Lan, Junyang Ren 외 arxiv

Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world problems. To sustain this capability on …

Information Retrieval

Deep Thinking by Markov Chain of Continuous Thoughts

2025-09-29 · Jiayu Liu, Zhenya Huang, Xuan Yang, Tianyun Ji 외 arxiv

Transformer-based models can perform complicated reasoning by generating reasoning paths token by token. While effective, this approach often requires generating thousands of tokens to solve a single problem, which can b…

MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning

2025-05-23 · Yusheng Zhao, Xiao Luo, Weizhi Zhang, Wei Ju 외

The ability to reason is one of the most fundamental capabilities of large language models (LLMs), enabling a wide range of downstream tasks through sophisticated problem-solving. A critical aspect of this is code reason…

Logical Reasoning