# Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests

arXiv: https://arxiv.org/abs/2610.12849 · HTML: https://mlsanity.com/paper/2610.12849/

## 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 12 of its 45 references that are in the map.
- First posted on arXiv 9 Oct 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, 12 of 12)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Productivity Assessment of Neural Code Completion](https://mlsanity.com/paper/2205.06537/) (2022)
- [Taxonomy of Attacks on Open-Source Software Supply Chains](https://mlsanity.com/paper/2204.04008/) (2022)
- [Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study](https://mlsanity.com/paper/2403.08604/) (2024)
- [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026)
- [Automating Dependency Updates in Practice: An Exploratory Study on GitHub Dependabot](https://mlsanity.com/paper/2206.07230/) (2022)
- [Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub](https://mlsanity.com/paper/2601.15195/) (2026)
- [How to Design a Program Repair Bot? Insights from the Repairnator Project](https://mlsanity.com/paper/1811.09852/) (2018)
- [DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle](https://mlsanity.com/paper/2601.20882/) (2026)
- [Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time](https://mlsanity.com/paper/2604.00917/) (2026)
- [Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study](https://mlsanity.com/paper/2605.22534/) (2026)
- [Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests](https://mlsanity.com/paper/2601.18749/) (2026)

## Abstract (arXiv)

Current software engineering agents are evaluated predominantly inside isolated sandboxes against synchronous local tests. However, deploying features in collaborative repositories requires modifying continuous integration (CI/CD) pipelines, containers, and provisioning manifests alongside application logic. Because agents lack deployment awareness, attempting cross-domain modifications introduces unverified dependencies into asynchronous integration pipelines. To isolate the causal integration overhead of dual-scope pull requests (PRs)-modifying both application code and deployment infrastructure-we evaluated 26,999 PRs across two large datasets (AIDev v5 and MOSAIC-3M) encompassing six agent architectures and an aligned human baseline. Using a deterministic four-tier file taxonomy and an exact 4D strata-matching framework, we isolated integration metrics under conditional exchangeability while controlling for application volume. We find agents operate primarily as application coders or chore workers, with maintenance tasks capturing 17.70% to 25.41% of agent PRs. Dual-scope modifications represent only 4.48% to 4.55% of agentic PRs, yet trigger bimodal integration outcomes. In the first mode, explicitly reviewed contributions experience protracted delays, adding a median penalty of +13.13 hours and multiplying time-to-merge by 3.24x, driven mechanically by CI/CD and provisioning manifests. In the second mode, maintainer gatekeeping exhibits a structural bypass: even for external contributors lacking repository write access, agent identity reduces the odds of human review by 63.7% compared to human peers. Consequently, 43.1% to 56.2% of dual-scope PRs bypass inspection to merge silently in a median of under 31 minutes. These uninspected modifications compromise build verification, demonstrating the need for deployment-aware benchmarks and strict path-based access controls.