Call for Papers — EMSE Special Issue on “Agentic Software Engineering: The Rise of AI Teammates”

A special issue of the Empirical Software Engineering Journal.

Editors of the Special Issue

• Ahmed E. Hassan, (Queen’s University, Canada), ahmed@cs.queensu.ca
• Hao Li, (Queen’s University, Canada), hao.li@queensu.ca
• Haoxiang Zhang, (Queen’s University, Canada), haoxiang.zhang@queensu.ca

Description of the Special Issue

AI agents are rapidly reshaping the landscape of software engineering by autonomously developing features, fixing bugs, and writing tests. AI agents such as Claude Code, Cursor, Devin, GitHub Copilot, and OpenAI Codex are no longer just assisting developers; they are becoming active AI teammates in the software development process. Despite their growing presence, the research community lacks a comprehensive, large-scale understanding of how AI agents collaborate with developers in real-world projects: how they propose code changes, how developers respond, and what kinds of collaboration patterns emerge.

As AI teammates move beyond simple code completion to performing complex tasks such as implementing features, managing pull requests, and orchestrating multi-step workflows, they generate a vast new category of digital artifacts. Understanding the behaviors, limitations, and collaborative impacts of these AI teammates is essential for ensuring that human-agent collaboration delivers high-quality, trustworthy software. This special issue provides a dedicated venue for rigorous, in-depth studies that advance our understanding of this rapidly evolving field.

To support research in this domain, the publicly available AIDev dataset (hosted on Hugging Face and Zenodo) captures around one million agent-authored pull requests from real-world GitHub repositories. We encourage authors to leverage AIDev for their empirical studies, although the use of this dataset is not mandatory. Prospective authors can explore the accepted MSR challenge papers at https://2026.msrconf.org/track/msr-2026-mining-challenge to see what has already been studied and to find inspiration for their own work.

Topics of Interest

We invite high-quality research that investigates the following (but not limited to) topics:

• Human-Agent Collaboration: The shift from direct coding to orchestration, including new artifacts, cognitive load, trust calibration, and processes required for effective human-agent collaboration.

• Mining Agent-Generated Artifacts: Novel data mining and knowledge discovery techniques applied to the artifacts generated by AI agents.

• Architectures for Agents: Composition strategies, tool use, memory management, and multi-agent coordination patterns.

• Quality and Maintenance: Empirical evaluations of agent-authored code, including trade-offs such as speed versus trust, code consistency, and long-term maintenance challenges.

• Review Dynamics: The evolving nature of code review in the presence of AI teammates, including the role of AI reviewers and the balance between review speed and depth.

• Failure Patterns and Risks: Taxonomies of agent failures, security vulnerabilities, supply chain risks, and challenges related to attributing authorship in AI-generated code.

• Testing and Evaluation: How AI agents contribute tests, evaluation of agents on repository-level tasks, and developer interventions to ensure reliable software testing.

• Production Operations: Monitoring, debugging, release engineering, and maintaining agentic systems (MLOps, LLMOps, AgentOps) in production environments.

• Safety, Ethics, and Compliance: Trustworthiness of agent-generated artifacts, fairness, transparency, and regulatory considerations for AI-authored code.

• Economic Cost and Impact: Studies on the productivity, cost-effectiveness, and broader economic implications of adopting AI teammates.

Schedule

This special issue follows a rolling review process. Authors are encouraged to submit their papers as soon as they are ready rather than waiting for the final deadline. The review process will begin promptly upon receiving each submission, and accepted papers will be published online continuously as they are finalized.

• Final Submission Deadline: September 28, 2026

Submission Instructions

Papers should be submitted through the Empirical Software Engineering editorial manager website (http://www.editorialmanager.com/emse/) as follows (1) select “Research Papers” and (2) later on the Additional Information page:

• Answer “Yes” to “Does this paper belong to a special issue?”
• And select “Agentic Software Engineering” for “Please select the issue your manuscript belongs to”.
• In the cover letter, please explicitly explain why the submission fits with the special issue and, in case of extensions of conference papers, what additional research is included with respect to the conference version.

For formatting guidelines as well as submission instructions, visit http://www.springer.com/computer/swe/journal/10664?detailsPage=pltci_2530593