Will It Survive? Deciphering the Fate of AI-Generated Code in Open Source

TL;DR

This study analyzes the longevity and modification patterns of AI-generated code in open source projects, revealing it survives longer than human code but faces different modification dynamics, with organizational factors influencing its long-term viability.

Contribution

It provides empirical evidence that AI-generated code persists longer than human code and highlights the importance of organizational practices over generation quality for its sustainability.

Findings

AI-generated code has a 16% lower hazard of modification.

Agent-authored code shows slightly higher corrective modification rates.

Textual features can predict modification-prone code with moderate accuracy.

Abstract

The integration of AI agents as coding assistants into software development has raised questions about the long-term viability of AI agent-generated code. A prevailing hypothesis within the software engineering community suggests this code is "disposable", meaning it is merged quickly but discarded shortly thereafter. If true, organizations risk shifting maintenance burden from generation to post-deployment remediation. We investigate this hypothesis through survival analysis of 201 open-source projects, tracking over 200,000 code units authored by AI agents versus humans. Contrary to the disposable code narrative, agent-authored code survives significantly longer: at the line level, it exhibits a 15.8 percentage-point lower modification rate and 16% lower hazard of modification (HR = 0.842, p < 0.001). However, modification profiles differ. Agent-authored code shows modestly elevated corrective rates (26.3% vs. 23.0%), while human code shows higher adaptive rates. However, the effect sizes are small (Cram\'er's V = 0.116), and per-agent variation exceeds the agent-human gap. Turning to prediction, textual features can identify modification-prone code (AUC-ROC = 0.671), but predicting when modifications occur remains challenging (Macro F1 = 0.285), suggesting timing depends on external organizational dynamics. The bottleneck for agent-generated code may not be generation quality, but the organizational practices that govern its long-term evolution.