# A Study of Library Usage in Agent-Authored Pull Requests

arXiv: https://arxiv.org/abs/2512.11589 · HTML: https://mlsanity.com/paper/2512.11589/

## Key facts

- Cited by 1 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 9 of its 27 references that are in the map.
- First posted on arXiv 12 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, 9 of 9)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion](https://mlsanity.com/paper/2406.09834/) (2024)
- [An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project](https://mlsanity.com/paper/2401.16186/) (2024)
- [SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments](https://mlsanity.com/paper/2507.09063/) (2025)
- [Automating Dependency Updates in Practice: An Exploratory Study on GitHub Dependabot](https://mlsanity.com/paper/2206.07230/) (2022)
- [ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration](https://mlsanity.com/paper/2412.05366/) (2024)
- [On the Impact of Micro-Packages: An Empirical Study of the npm JavaScript Ecosystem](https://mlsanity.com/paper/1709.04638/) (2017)
- [The role of library versions in Developer-ChatGPT conversations](https://mlsanity.com/paper/2401.16340/) (2024)

## Built on by (most cited first, 1 of 1)

- [Can Agents Design Libraries for Agents?](https://mlsanity.com/paper/2609.36730/) (2026)

## Abstract (arXiv)

Coding agents are becoming increasingly capable of completing end-to-end software engineering workflows that previously required a human developer, including raising pull requests (PRs) to propose their changes. However, we still know little about how these agents use libraries when generating code, a core part of real-world software development. To fill this gap, we study 26,760 agent-authored PRs from the AIDev dataset to examine three questions: how often do agents import libraries, how often do they introduce new dependencies (and with what versioning), and which specific libraries do they choose? We find that agents often import libraries (29.5% of PRs) but rarely add new dependencies (1.3% of PRs); and when they do, they follow strong versioning practices (75.0% specify a version), an improvement on direct LLM usage where versions are rarely mentioned. Generally, agents draw from a surprisingly diverse set of external libraries, contrasting with the limited "library preferences" seen in prior non-agentic LLM studies. Our findings offer an early empirical view on how AI coding agents interact with today's software ecosystems.