# AI Writes Code, Humans Pay the Debt. An Empirical Study on the Sustainability and Evolution of Agent-Generated Code

arXiv: https://arxiv.org/abs/2609.04208 · HTML: https://mlsanity.com/paper/2609.04208/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 6 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 9 of 9)

- [Human-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexity](https://mlsanity.com/paper/2508.21634/) (2025)
- [Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models](https://mlsanity.com/paper/2407.00456/) (2024)
- [Code Readability in the Age of Large Language Models: An Industrial Case Study from Atlassian](https://mlsanity.com/paper/2501.11264/) (2025)
- [What Were You Thinking? An LLM-Driven Large-Scale Study of Refactoring Motivations in Open-Source Projects](https://mlsanity.com/paper/2509.07763/) (2025)
- [Evaluating Time-Dependent Methods and Seasonal Effects in Code Technical Debt Prediction](https://mlsanity.com/paper/2408.08095/) (2024)
- [On the Lack of Consensus Among Technical Debt Detection Tools](https://mlsanity.com/paper/2103.04506/) (2021)
- [AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development](https://mlsanity.com/paper/2605.02741/) (2026)
- [SQuaD: The Software Quality Dataset](https://mlsanity.com/paper/2511.11265/) (2025)
- [Can AI Agents Generate Microservices? How Far are We?](https://mlsanity.com/paper/2603.09004/) (2026)

## Abstract (arXiv)

Context. The increasing adoption of Generative AI coding agents in software engineering is transforming how developers implement and maintain code. While these systems provide short-term productivity benefits, their long-term impact on software quality and technical debt remains unclear. Aim. We aim to investigate how agent-generated code affects software quality, focusing on issue localization accuracy, the introduction of technical debt, and its evolution over time. Method. We will conduct a large-scale mining software repositories study using the SQuaD dataset, employing a candidate set of 628k issue tickets. We will generate agent-based implementations for these issues, and compare them with the actual commits done by developers using static analysis metrics and tools. We will analyze differences at the commit level and across releases, and we will consider multiple LLM-based Agents selected through a systematic benchmarking strategy. Expected Results. We expect to provide empirical evidence on the trade-offs introduced by agent-based development, including differences in localization accuracy, variations in technical debt introduction, and potential divergence in long-term evolution. We expect the results to highlight variability across LLMs, to enrich our understanding of software evolution with Agents, and to inform more responsible adoption of Agents in software development.