# Characterizing the Quality Profile of AI-Generated C++ in Production

arXiv: https://arxiv.org/abs/2608.06640 · HTML: https://mlsanity.com/paper/2608.06640/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants](https://mlsanity.com/paper/2208.09727/) (2022)
- [Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming](https://mlsanity.com/paper/2210.14306/) (2022)
- [Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues](https://mlsanity.com/paper/2307.12596/) (2023)
- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [Language Models for Code Completion: A Practical Evaluation](https://mlsanity.com/paper/2402.16197/) (2024)
- [LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion](https://mlsanity.com/paper/2406.09834/) (2024)
- [Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models](https://mlsanity.com/paper/2406.08731/) (2024)
- [Traces of Memorisation in Large Language Models for Code](https://mlsanity.com/paper/2312.11658/) (2023)
- [Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications](https://mlsanity.com/paper/2503.01245/) (2025)
- [Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects](https://mlsanity.com/paper/2511.04427/) (2025)
- [How much does AI impact development speed? An enterprise-based randomized controlled trial](https://mlsanity.com/paper/2410.12944/) (2024)
- [AI-Assisted Assessment of Coding Practices in Modern Code Review](https://mlsanity.com/paper/2405.13565/) (2024)
- [The Role of Generative AI in Software Development Productivity: A Pilot Case Study](https://mlsanity.com/paper/2406.00560/) (2024)
- [Static Analysis as a Feedback Loop: Enhancing LLM-Generated Code Beyond Correctness](https://mlsanity.com/paper/2508.14419/) (2025)
- [Dear Diary: A randomized controlled trial of Generative AI coding tools in the workplace](https://mlsanity.com/paper/2410.18334/) (2024)
- [Generating Energy-Efficient Code via Large-Language Models -- Where are we now?](https://mlsanity.com/paper/2509.10099/) (2025)
- [Measuring the Runtime Performance of C++ Code Written by Humans using GitHub Copilot](https://mlsanity.com/paper/2305.06439/) (2023)
- [Correctness isnt Efficiency: Runtime Memory Divergence in LLM-Generated Code](https://mlsanity.com/paper/2601.01215/) (2026)
- [Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs](https://mlsanity.com/paper/2405.13932/) (2024)
- [How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuning](https://mlsanity.com/paper/2501.17501/) (2025)

## Abstract (arXiv)

The widespread integration of AI coding assistants offers undeniable boosts to engineering velocity. Yet, recent studies point to a growing trade-off, revealing persistent challenges with code quality and maintainability. Industry leaders, including frontier AI labs, echo these concerns. As large language models are increasingly relied upon to author production code, understanding their impact on shipped software quality has become a critical priority. However, assessing these effects in industrial workflows remains difficult due to observability barriers. We study the impact of AI-generated code on production quality within a large enterprise operating global products relied upon by billions of users daily. Driven by this scale and user trust, the organization values code quality and has built thorough observability for every line of code deployed into production, enabling us to overcome measurement barriers to assess these effects. This study presents a large-scale empirical analysis of AI-generated C++ code from April 2025 to April 2026, tracking 3.52 million code changes across this enterprise's brownfield codebase. The core purpose is to understand the quality, performance, and maintenance characteristics of AI-generated code compared to human-written code in a production environment at scale. We find that AI-generated C++ code has a distinct quality profile, showing higher rates of interface and coupling burdens, copy and allocation overheads, and a reliance on explicit loops over optimized standard APIs. These issues translate into tangible downstream costs, including increased review effort and a 5-8% increase in compute resource consumption. However, we demonstrate that providing models with targeted, taxonomy-informed feedback can mitigate these effects, leading to an 11.1% reduction in targeted static analysis warnings and improved computational efficiency.