# (Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding

arXiv: https://arxiv.org/abs/2607.26375 · HTML: https://mlsanity.com/paper/2607.26375/

## Key facts

- Cited by 2 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 15 of its 108 references that are in the map.
- First posted on arXiv 29 Jul 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, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task](https://mlsanity.com/paper/2506.08872/) (2025)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [How AI Impacts Skill Formation](https://mlsanity.com/paper/2601.20245/) (2026)
- [Composer 2 Technical Report](https://mlsanity.com/paper/2603.24477/) (2026)
- [AI Assistance Reduces Persistence and Hurts Independent Performance](https://mlsanity.com/paper/2604.04721/) (2026)
- [SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery](https://mlsanity.com/paper/2602.21136/) (2026)
- [More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests](https://mlsanity.com/paper/2601.21276/) (2026)
- [Completion neq Collaboration: Scaling Collaborative Effort with Agents](https://mlsanity.com/paper/2510.25744/) (2025)
- [LiteraryTaste: A Preference Dataset for Creative Writing Personalization](https://mlsanity.com/paper/2511.09310/) (2025)
- [Assessing Problem Decomposition in CS1 for the GenAI Era](https://mlsanity.com/paper/2511.05764/) (2025)
- [How do Agents Refactor: An Empirical Study](https://mlsanity.com/paper/2601.20160/) (2026)
- [Why Human Guidance Matters in Collaborative Vibe Coding](https://mlsanity.com/paper/2602.10473/) (2026)

## Built on by (most cited first, 2 of 2)

- [A Case Study in Assuring AI-Written Software](https://mlsanity.com/paper/2610.08651/) (2026)
- [Code Understanding is a Bottleneck for Coding Agents](https://mlsanity.com/paper/2610.10610/) (2026)

## Abstract (arXiv)

Coding agents (e.g., Cursor) improve developer productivity by optimizing task completion, but shifting users from writing code to prompting and reviewing may harm their understanding, impeding oversight, learning, and communication. To probe this, we have 54 students create a website with one of two AI systems: an agent that edits user code; or a chatbot where users write code alone or adapt generic code snippets. We test understanding via comprehension questions and a task where users extend their code without agents, showing: (1) While agents aid initial task completion, they harm users' code comprehension and thus do not prepare users to extend their code; (2) Low-effort agent interaction types, like copy+paste prompts and auto-accepted edits, are linked with lower comprehension; and (3) Despite self-reported weaker understanding, users still prefer coding agents because they are quick and easy to use. While users stay in the loop for coding workflows, understanding should not be forgotten. Towards this goal, we distill our analyses into future research directions for coding agent developers: dissuading low-effort prompting, creating readable code, and promoting active engagement.