Scholarlink

<p>Energy efficiency has become a central concern in the deployment of AI systems. While most research targets hardware-level acceleration to reduce energy consumption, software-based strategies remain underexplored or often sacrifice performance. In this work, we present a software-oriented approach for embedded code generation using a multi-agent pipeline composed of small, locally executed LLMs. Our architecture divides the generation process into reasoning stages, aiming to reduce resource demands without relying on cloud services. We evaluated our system using real-world measurements of energy and memory consumption, comparing multiple model configurations and execution scenarios. The results suggest that running small LLMs locally is a feasible path for software generation under constrained resources, contributing to the broader discussion on low-energy AI without specialized hardware.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Software Generation for Embedded Systems with Low-Cost LLMs: An Energy Evaluation Discussion

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月12日

查看全文
  • Marcos L. K. Reckers,
  • Nathan A. Guimarães,
  • Luigi Carro

摘要

Energy efficiency has become a central concern in the deployment of AI systems. While most research targets hardware-level acceleration to reduce energy consumption, software-based strategies remain underexplored or often sacrifice performance. In this work, we present a software-oriented approach for embedded code generation using a multi-agent pipeline composed of small, locally executed LLMs. Our architecture divides the generation process into reasoning stages, aiming to reduce resource demands without relying on cloud services. We evaluated our system using real-world measurements of energy and memory consumption, comparing multiple model configurations and execution scenarios. The results suggest that running small LLMs locally is a feasible path for software generation under constrained resources, contributing to the broader discussion on low-energy AI without specialized hardware.