# MaintainCoder: Maintainable Code Generation Under Dynamic Requirements

arXiv: https://arxiv.org/abs/2503.24260 · HTML: https://mlsanity.com/paper/2503.24260/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [Self-Evolving Multi-Agent Collaboration Networks for Software Development](https://mlsanity.com/paper/2410.16946/) (2024)
- [A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends](https://mlsanity.com/paper/2311.10372/) (2023)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code](https://mlsanity.com/paper/2311.07989/) (2023)
- [HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation](https://mlsanity.com/paper/2412.21199/) (2024)
- [Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models](https://mlsanity.com/paper/2407.11470/) (2024)

## Built on by (most cited first, 14 of 14)

- [SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks](https://mlsanity.com/paper/2603.24755/) (2026)
- [CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation](https://mlsanity.com/paper/2504.21751/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Controlled Self-Evolution for Algorithmic Code Optimization](https://mlsanity.com/paper/2601.07348/) (2026)
- [SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades](https://mlsanity.com/paper/2605.14415/) (2026)
- [Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time](https://mlsanity.com/paper/2604.00917/) (2026)
- [A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX](https://mlsanity.com/paper/2603.27296/) (2026)
- [Is Agent Code Less Maintainable Than Human Code?](https://mlsanity.com/paper/2606.21804/) (2026)
- [Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study](https://mlsanity.com/paper/2602.10140/) (2026)
- [SpecPath: Testing Coding Agents Across Contract-Equivalent Specification Histories](https://mlsanity.com/paper/2608.09799/) (2026)
- [MARS: Multi-Specialist LLM Relay System for Competitive Programming](https://mlsanity.com/paper/2608.23918/) (2026)
- [Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase](https://mlsanity.com/paper/2608.29310/) (2026)
- [Do Coding Agents Reuse Existing Code or Reinvent the Wheel?](https://mlsanity.com/paper/2609.35357/) (2026)
- [Definition Grounding in Theory-Level Auto-formalization](https://mlsanity.com/paper/2610.19223/) (2026)

## Abstract (arXiv)

Modern code generation has made significant strides in functional correctness and execution efficiency. However, these systems often overlook a critical dimension in real-world software development: maintainability. To handle dynamic requirements with minimal rework, we propose MaintainCoder as a pioneering solution. It integrates the Waterfall model, design patterns, and multi-agent collaboration to systematically enhance cohesion, reduce coupling, achieving clear responsibility boundaries and better maintainability. We also introduce MaintainCoder, a benchmark comprising requirement changes and novel dynamic metrics on maintenance efforts. Experiments demonstrate that existing code generation methods struggle to meet maintainability standards when requirements evolve. In contrast, MaintainCoder improves dynamic maintainability metrics by more than 60% with even higher correctness of initial codes. Furthermore, while static metrics fail to accurately reflect maintainability and even contradict each other, our proposed dynamic metrics exhibit high consistency. Our work not only provides the foundation for maintainable code generation, but also highlights the need for more realistic and comprehensive code generation research. Resources: https://github.com/IAAR-Shanghai/MaintainCoder.