Saved in:
Bibliographic Details
Main Authors: Ma, Hongru, Liang, Yanjie, Si, Jiasheng, Zhang, Weiyu, Guan, Hongjiao, Zheng, Chaoqun, Xu, Bing, Lu, Wenpeng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.00532
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Large language models (LLMs) have revolutionized code generation, significantly enhancing developer productivity. However, for a vast number of users with minimal coding knowledge, LLMs provide little support, as they primarily generate isolated code snippets rather than complete, large-scale project code. Without coding expertise, these users struggle to interpret, modify, and iteratively refine the outputs of LLMs, making it impossible to assemble a complete project. To address this issue, we propose Self-Rectified Large-Scale Code Generator (SRLCG), a framework that generates complete multi-file project code from a single prompt. SRLCG employs a novel multidimensional chain-of-thought (CoT) and self-rectification to guide LLMs in generating correct and robust code files, then integrates them into a complete and coherent project using our proposed dynamic backtracking algorithm. Experimental results show that SRLCG generates code 15x longer than DeepSeek-V3, 16x longer than GPT-4, and at least 10x longer than other leading CoT-based baselines. Furthermore, they confirm its improved correctness, robustness, and performance compared to baselines in large-scale code generation.