# AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents

arXiv: https://arxiv.org/abs/2512.22387 · HTML: https://mlsanity.com/paper/2512.22387/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 26 Dec 2025.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [A Step Toward Quantifying Independently Reproducible Machine Learning Research](https://mlsanity.com/paper/1909.06674/) (2019)
- [An Empirical Comparison of Dependency Network Evolution in Seven Software Packaging Ecosystems](https://mlsanity.com/paper/1710.04936/) (2017)
- [Assessing Consistency and Reproducibility in the Outputs of Large Language Models: Evidence Across Diverse Finance and Accounting Tasks](https://mlsanity.com/paper/2503.16974/) (2025)
- [A Reproducibility and Generalizability Study of Large Language Models for Query Generation](https://mlsanity.com/paper/2411.14914/) (2024)
- [Sciunits: Reusable Research Objects](https://mlsanity.com/paper/1707.05731/) (2017)

## Built on by (most cited first, 5 of 5)

- [Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality](https://mlsanity.com/paper/2607.03691/) (2026)
- [A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives](https://mlsanity.com/paper/2602.21351/) (2026)
- [TDD Governance for Multi-Agent Code Generation via Prompt Engineering](https://mlsanity.com/paper/2604.26615/) (2026)
- [RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue](https://mlsanity.com/paper/2607.01213/) (2026)
- [From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents](https://mlsanity.com/paper/2609.36161/) (2026)

## Abstract (arXiv)

The rise of Large Language Models (LLMs) as coding agents promises to accelerate software development, but their impact on generated code reproducibility remains largely unexplored. This paper presents an empirical study investigating whether LLM-generated code can be executed successfully in a clean environment with only OS packages and using only the dependencies that the model specifies. We evaluate three state-of-the-art LLM coding agents (Claude Code, OpenAI Codex, and Gemini) across 300 projects generated from 100 standardized prompts in Python, JavaScript, and Java. We introduce a three-layer dependency framework (distinguishing between claimed, working, and runtime dependencies) to quantify execution reproducibility. Our results show that only 68.3% of projects execute out-of-the-box, with substantial variation across languages (Python 89.2%, Java 44.0%). We also find a 13.5 times average expansion from declared to actual runtime dependencies, revealing significant hidden dependencies.