# Collaborator or Assistant? How AI Coding Agents Partition Work Across Pull Request Lifecycles

arXiv: https://arxiv.org/abs/2605.08017 · HTML: https://mlsanity.com/paper/2605.08017/

## 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 8 of its 30 references that are in the map.
- First posted on arXiv 8 May 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, 8 of 8)

- [Agentic AI Software Engineers: Programming with Trust](https://mlsanity.com/paper/2502.13767/) (2025)
- [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026)
- [How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering](https://mlsanity.com/paper/2501.08774/) (2025)
- [AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development](https://mlsanity.com/paper/2601.13597/) (2026)
- [On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source](https://mlsanity.com/paper/2601.13754/) (2026)
- [Understanding the Challenges and Opportunities of Generative AI Apps: An Empirical Study](https://mlsanity.com/paper/2506.16453/) (2025)
- [Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance](https://mlsanity.com/paper/2602.08915/) (2026)
- [A Task-Level Evaluation of AI Agents in Open-Source Projects](https://mlsanity.com/paper/2602.02345/) (2026)

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

- [Early Adoption of Agentic Coding Tools by GitHub Projects](https://mlsanity.com/paper/2607.14037/) (2026)
- [Working with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work](https://mlsanity.com/paper/2609.29901/) (2026)

## Abstract (arXiv)

When AI coding agents open branches and submit pull requests (PRs), two questions co-determine oversight design: who starts the work (operational agency) and who authorizes its completion (merge governance). We characterize tools along a Collaborator-Assistant spectrum in how they redistribute initiative, oversight, and endorsement, while merge governance remains predominantly human across five tools (OpenAI, Copilot, Devin, Cursor, Claude Code). We analyze 29,585 PR lifecycles using an Initiator x Approver taxonomy with six interaction scenarios; lifecycle reconstruction supplies the how behind those roles. Collaborator tools (Cursor, Devin, Copilot) concentrate operational initiative in agents that open and carry PR work forward, with humans retaining review and endorsement on the path to merge; Assistant tools (OpenAI, Claude) leave task direction primarily with humans and supply bounded support within human-led workflows. Across the spectrum, agency and governance decouple: Collaborator workflows are >=96% agent initiated, yet terminal merge authority remains almost exclusively human, with agent-classified approvers confined to a small fraction of PRs. Where automation executes a merge, logs record the executor but not the decision-maker, marking a boundary of observation. We contribute the taxonomy, per-tool state machines, and a replication package for research on automation, oversight, and governance in PR workflows.