Evaluating Classical Software Process Models as Coordination Mechanisms for LLM-Based Software Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915499284103168 |
|---|---|
| author | Ha, Duc Minh Kien, Phu Trac Quan, Tho Nguyen-Duc, Anh |
| author_facet | Ha, Duc Minh Kien, Phu Trac Quan, Tho Nguyen-Duc, Anh |
| contents | [Background] Large Language Model (LLM)-based multi-agent systems (MAS) are transforming software development by enabling autonomous collaboration. Classical software processes such asWaterfall, V-Model, and Agile offer structured coordination patterns that can be repurposed to guide these agent interactions. [Aims] This study explores how traditional software development processes can be adapted as coordination scaffolds for LLM based MAS and examines their impact on code quality, cost, and productivity. [Method] We executed 11 diverse software projects under three process models and four GPT variants, totaling 132 runs. Each output was evaluated using standardized metrics for size (files, LOC), cost (execution time, token usage), and quality (code smells, AI- and human detected bugs). [Results] Both process model and LLM choice significantly affected system performance. Waterfall was most efficient, V-Model produced the most verbose code, and Agile achieved the highest code quality, albeit at higher computational cost. [Conclusions] Classical software processes can be effectively instantiated in LLM-based MAS, but each entails trade-offs across quality, cost, and adaptability. Process selection should reflect project goals, whether prioritizing efficiency, robustness, or structured validation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13942 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating Classical Software Process Models as Coordination Mechanisms for LLM-Based Software Generation Ha, Duc Minh Kien, Phu Trac Quan, Tho Nguyen-Duc, Anh Software Engineering [Background] Large Language Model (LLM)-based multi-agent systems (MAS) are transforming software development by enabling autonomous collaboration. Classical software processes such asWaterfall, V-Model, and Agile offer structured coordination patterns that can be repurposed to guide these agent interactions. [Aims] This study explores how traditional software development processes can be adapted as coordination scaffolds for LLM based MAS and examines their impact on code quality, cost, and productivity. [Method] We executed 11 diverse software projects under three process models and four GPT variants, totaling 132 runs. Each output was evaluated using standardized metrics for size (files, LOC), cost (execution time, token usage), and quality (code smells, AI- and human detected bugs). [Results] Both process model and LLM choice significantly affected system performance. Waterfall was most efficient, V-Model produced the most verbose code, and Agile achieved the highest code quality, albeit at higher computational cost. [Conclusions] Classical software processes can be effectively instantiated in LLM-based MAS, but each entails trade-offs across quality, cost, and adaptability. Process selection should reflect project goals, whether prioritizing efficiency, robustness, or structured validation. |
| title | Evaluating Classical Software Process Models as Coordination Mechanisms for LLM-Based Software Generation |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2509.13942 |