Scholarlink

<p>Large language models (LLMs) have the potential to revolutionize how we design and implement compilers and code translation tools. However, existing LLMs struggle to handle long and complex programs. We introduce LEGO-Compiler, a novel neural compilation system that leverages LLMs to translate high-level languages into assembly code. Our approach centers on three key innovations: LEGO translation, which decomposes the input program into manageable blocks; breaking down the complex compilation process into smaller, simpler verifiable steps by organizing it as a verifiable LLM workflow by external tests; and a feedback mechanism for self-correction. Supported by formal proofs of translation composability, LEGO-Compiler demonstrates high accuracy on multiple datasets, including over 99% on ExeBench and 97.9% on industrial-grade AnsiBench. Additionally, LEGO-Compiler has also achieved a near one order-of-magnitude improvement on compilable code size scalability. This work opens new avenues for applying LLMs to system-level tasks, complementing traditional compiler technologies.</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

LEGO-compiler: enhancing neural compilation through translation composability

  • 期刊论文

  • 发表日期：

    2026年4月13日

查看全文
  • Shuoming Zhang,
  • Jiacheng Zhao,
  • Qiuchu Yu,
  • Chunwei Xia,
  • Zheng Wang,
  • Yunji Chen,
  • Xiaobing Feng,
  • Huimin Cui

摘要

Large language models (LLMs) have the potential to revolutionize how we design and implement compilers and code translation tools. However, existing LLMs struggle to handle long and complex programs. We introduce LEGO-Compiler, a novel neural compilation system that leverages LLMs to translate high-level languages into assembly code. Our approach centers on three key innovations: LEGO translation, which decomposes the input program into manageable blocks; breaking down the complex compilation process into smaller, simpler verifiable steps by organizing it as a verifiable LLM workflow by external tests; and a feedback mechanism for self-correction. Supported by formal proofs of translation composability, LEGO-Compiler demonstrates high accuracy on multiple datasets, including over 99% on ExeBench and 97.9% on industrial-grade AnsiBench. Additionally, LEGO-Compiler has also achieved a near one order-of-magnitude improvement on compilable code size scalability. This work opens new avenues for applying LLMs to system-level tasks, complementing traditional compiler technologies.