Main TrackAIware 2026

Accepted Papers

	Title
	Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap Main Track Christoph Treude DOI Pre-print
	An Empirical Study of Reasoning Steps in Thinking Code LLMsAIware Honorable Mention Paper Award Main Track Haoran Xue, Gias Uddin, Song Wang DOI
	A Preliminary Study on Explaining Risk of Code Changes using LLM-Based Prediction Models Main Track Yalin Liu, Kosay Jabre, Rui Abreu, Zachariah J Carmichael, Vijayaraghavan Murali, Akshay Patel, Jun Ge, Weiyan Sun, Cong Zhang, Audris Mockus, David Khavari, Peter Rigby, Nachiappan Nagappan DOI
	Artifact Readiness Gates with Saturation Stop Rules and Host-Parity Admissibility for FM Release Evaluation Main Track Yanick Kanyiki DOI
	Auditing Who Appears to Belong: A Large-Scale Empirical Study of Bias in Deployed Text-to-Image Systems for Software Engineering Main Track Mohamad Kassab DOI
	Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation Main Track Fazle Rabbi, Soumit Kanti Saha, Jinqiu Yang DOI
	Can LLMs Really Reason about Code? Studying How Well LLMs Understand the Relation between Input, Code, and Output Main Track Norman Becker, Tural Mammadov, Andreas Zeller Link to publication DOI File Attached
	Collaborator or Assistant? How AI Coding Agents Partition Work across Pull Request Lifecycles Main Track Young Jo Chung, Safwat Hassan DOI
	Co-located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation Main Track Éric Jacopin DOI
	Configuring Agentic AI Coding Tools: An Exploratory Study Main Track Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla, Muhammad Auwal Abubakar, Christoph Treude, Sebastian Baltes DOI Pre-print
	Detecting Unsoundness in Neural Network Verifiers via Concrete–Abstract Consistency Main Track Kaijie Liu, Yulei Sui DOI Pre-print
	Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python ModernizationAIware Honorable Mention Paper Award Main Track Naing Oo Lwin, Rajesh Kumar DOI
	Examining LLMs Ability to Summarize Code Through Mutation-Analysis Main Track Lara Khatib, Michael Pu, Bogdan Vasilescu, Mei Nagappan
	Executable but Unlearnable: Designing Code That Resists LLM-Based Learning Main Track Viraaji Mothukuri, Reza M. Parizi DOI
	Fixpad++: Automated Bug Fix Verification using LLM AgentsAIware Honorable Mention Paper Award Main Track Mustafa Özkan İr, Mehmet Dedeler, Anil Koyuncu, Eray Tüzün DOI
	From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines Main Track Marcus Barnes, Taher A. Ghaleb, Safwat Hassan DOI Pre-print
	From Code Review to Spec-Driven Contracts: A Vision for Auditable AIWare Systems Main Track Mohammad Hamdaqa, Moataz Chouchen DOI
	From Correctness to Consistency: Redefining Reliability for the Agentware Era Main Track Xue Qin, Mauricio Gouvea Gruppi DOI
	How Robustly Do LLMs Understand Execution Semantics? Main Track Claudio Spiess, Premkumar Devanbu, Earl T. Barr DOI
	Is Artificial Intelligence an Elixir to the Software Engineering Community? An Empirical Study among Managers Main Track Xin Zhao, Brian Vu, Sitesh Pattanaik DOI
	Kubernetes Misconfigurations in the Wild: Taxonomy, Evolution, and Automated Repair with Large Language Models Main Track GHORAB Mostafa Anouar, Ahmad Abdellatif, Mohamed Aymen saied DOI
	Neural-Symbolic Multi-objective Optimization for Performance-Aware ORM Database Design Main Track Sasan Azizian, Ayoub Hazrati, Artin Azizian, Elham Rastegari, Hamid Bagheri, Juan Cui DOI
	Operationalizing Ethics for AI Agents: How Developers Encode Values into Repository Context Files Main Track Christoph Treude, Sebastian Baltes, Marc Cheong DOI Pre-print
	Quality and Security Signals in AI-Generated Python Refactoring Pull RequestsAIware Honorable Mention Paper Award Main Track Mohamed Almukhtar, Anwar Ghammam, Hua Ming DOI Pre-print
	SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code Main Track Manisha Mukherjee, Vincent J. Hellendoorn DOI
	Testing AIware Systems: A Software Engineering SurveyAIware Honorable Mention Paper Award Main Track Karla Gonzalez, Mariam El Mezouar DOI
	Towards AI as a Collaborative Partner: A Taxonomy of AI Agent Behavior in Software Engineering Main Track Tao Dong, Sherry Shi, Harini Sampath, Andrew Macvean DOI Pre-print
	Towards Migrating Neural Network ImplementationsAIware Honorable Mention Paper Award Main Track Nadia Daoudi, Iván Alfonso, Jordi Cabot DOI
	TriORM: Workload-Aware Neural-Symbolic Multi-objective Optimization for ORM Mapping Design Main Track Sasan Azizian, Ayoub Hazrati, Artin Azizian, Elham Rastegari DOI
	Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development Main Track Srijita Basu, Viktor Kjellberg, Simin Sun, Bengt Haraldsson, Md Abu Ahammed Babu, Wilhelm Meding, Farnaz Fotrousi, Miroslaw Staron DOI File Attached
	Using Mutation-Analysis to Examine an LLM’s Ability to Summarize Code Main Track Lara Khatib, Michael Pu, Bogdan Vasilescu, Mei Nagappan DOI
	VeriTrans: Fine-Tuned LLM-Assisted NL→PL Translation via a Deterministic Neuro-symbolic Pipeline Main Track Xuan Liu, Dheeraj Kodakandla, Kushagra Srivastva, Mahfuza Farooque DOI
	VISOR: A Vision-Language Model-Based Test Oracle for Testing Robots Main Track Prasun Saurabh, Pablo Valle, Aitor Arrieta, Shaukat Ali, Paolo Arcaini DOI
	When AI Coding Assistants Leak Training Data: A Study of LLM Memorization in Code GenerationAIware Honorable Mention Paper Award Main Track Xiaoyu Cheng, Kundi Yao, Pengyu Nie, Weiyi Shang DOI
	When Code Authors Are Agents: A Large-Scale Study of Human–Agent Collaboration in Pull Requests Main Track Anthonia Oluchukwu Njoku, Zohreh Sharafi, Foutse Khomh DOI
	Wink: Recovering from Misbehaviors in Coding Agents Main Track Rahul Nanda, Chandra Maddila, Smriti Jha, Euna Mehnaz Khan, Satish Chandra, Matteo Paltenghi DOI
	Zombie Agents: Detecting Semantic Livelock in Long-Horizon Autonomous Software Main Track Simarjot Khanna DOI

Call for Papers – AIware 2026 Main Track

“Software for all and by all” is the future of humanity. AIware, i.e., AI-powered software, has the potential to democratize software creation. We must reimagine software and software engineering (SE), enabling individuals of all backgrounds to participate in its creation with higher reliability and quality. Over the past decade, software has evolved from human-driven Codeware to the first generation of AIware, known as Neuralware, developed by AI experts. Foundation Models (FMs, including Large Language Models or LLMs), like GPT, ushered in software’s next generation, Promptware, led by domain and prompt experts. However, this merely scratches the surface of the future of software. We are already witnessing the emergence of the next generation of software, Agentware, in which humans and intelligent agents jointly lead the creation of software. With the advent of brain-like World Models and brain-computer interfaces, we anticipate the arrival of Mindware, representing another generation of software. Agentware and Mindware promise greater autonomy and widespread accessibility, with non-expert individuals, known as Software Makers, offering oversight to autonomous agents.

The software engineering community will need to develop fundamentally new approaches and evolve existing ones, so they are suitable for a world in which software creation is within the reach of Software Makers of all levels of SE expertise, as opposed to solely expert developers. We must recognize a shift in where expertise lies in software creation and start making the needed changes in the type of research that is being conducted, the ways that SE is being taught, and the support that is offered to software makers.

The 3rd ACM International Conference on AI-powered Software (AIware 2026, https://conf.researchr.org/home/aiware-2026) will be hosted on Mon 6 July and Tue 7 July, 2026, in Montreal, Canada, co-located with FSE’26. AIware 2026 aims to bring different communities together in anticipation of the upcoming changes driven by FMs and look at them from the perspective of AI-powered software and its evolution. AIware 2026 promotes cross-disciplinary discussions, identifies emerging research challenges, and establishes a new research agenda for the community in the Foundation Model era.

New this year

• Fully Open Public Review Process This year’s AIware Main Track adopts a fully open and public peer-review process to increase transparency and accountability in peer review, and promote broader engagement and feedback beyond the program committee. All submissions, reviews, author responses, and discussions will be publicly visible on the OpenReview platform.

• Author-Reviewer Interaction An author response period with multi-round interaction will be incorporated. Authors will have the opportunity to clarify technical details, correct misunderstandings and respond to reviewer concerns in an open forum. Reviewers can also raise further questions during this period.

• Another Opportunity for Rejected Submissions To further support open science and broader dissemination of ideas, all rejected submissions to the Main Track will be invited to participate in the AIware ArXiv Track and have the opportunity to present their work at the conference. Papers in the ArXiv Track will be clearly labeled as non-archival and will not be blocked for submission to other venues.

Topics of Interest

Topics of interest of the AIware conference include, but are not limited to the following:

• How would future software look like in the FM era?
• Agents & SE
• How to integrate legacy software in future AIware?
• Do existing programming models (e.g., object-oriented or functional programming) and SE practices (e.g., test-driven development and agile) remain suitable for developing and maintaining software in the FM era?
• What roles do autonomous agents play in the development and maintenance of software in the FM era?
• How will inner and open source collaboration evolve in the FM era?
• What kind of release engineering practices do we need for FM-powered software applications?
• Are LLMOps comprehensive enough to capture the release engineering needs of AIware in the FM era?
• How do we debug and monitor AIware in the FM era?
• How should we change SE curriculum, training and mentoring in the FM era?
• How to evolve FMs from the perspective of AIware and its makers in the FM era?
• How do human interactions and perceptions shape the development and implementation of AIware in the FM era?
• How do we measure and improve the trustworthiness of AIware in the FM era?
• What are the implications and effectiveness of foundation models in improving software engineering practices and outcomes?
• How does AIware impact developer productivity?

Types of Submissions

The AIware Main Track welcomes submissions from both academia and industry. At least one author of each accepted paper must attend the conference and present the work.

We welcome the following types of contributions:

• Full research papers

• Applied research papers

• Case studies

• Vision papers

• Position and new-idea papers

• Literature reviews and surveys

Page Limits

All submissions must follow the ACM format with strict page limits (excluding references):

• Full-length papers (i.e. case studies, theoretical, applied research papers): 8 pages

• Short papers (i.e., vision, new ideas, and position papers): 2–4 pages

• Literature reviews and surveys: 14–20 pages

Up to 1–2 additional pages are allowed for references only.

Awards and Journal Invitations

• The best full-length papers will be recognized with the ACM SIGSOFT Distinguished Paper Awards.

• Selected accepted papers will be invited to be substantially revised and extended for a special issue of Empirical Software Engineering (published by Springer).

Submission Guidelines

All authors should use the official “ACM Primary Article Template” as can be obtained from the ACM Proceedings Template page. LaTeX users should use the following latex code at the start of the LaTeX document where the review option produces line numbers for easy reference by the reviewers and the anonymous optician omits author names:

\documentclass[sigconf,review,anonymous]{acmart}

Papers must be submitted electronically in OpenReview platform through the following submission site: https://openreview.net/group?id=ACM.org/AIWare/2026/Conference

Authors are required to sign up active OpenReview accounts for submission. (Institutional email is recommended for registration otherwise it might take a couple of days for OpenReview to manually activate the account.) Instructions for account signing-up. Please visit http://openreview.net/profile after logging in, complete your profile and import your publications. Publications can be automatically imported from DBLP. Instructions for importing publications.

All submissions must be in PDF. All papers must be written in English.

All submissions are subject to ACM policies including ACM Publications Policies, ACM’s new Publications Policy on Research Involving Human Participants and Subjects, ACM Policy and Procedures on Plagiarism, ACM Policy on Prior Publication and Simultaneous Submissions, and the ACM Policy on Authorship and its accompanying FAQ released April 20, 2023. In particular, authors should pay attention to the following points:

• Generative AI tools and technologies, such as ChatGPT, may not be listed as authors of an ACM-published Work. The use of generative AI tools and technologies to create content is permitted but must be fully disclosed in the Work. For example, the authors could include the following statement in the Acknowledgements section of the Work: ChatGPT was used to generate sections of this Work, including text, tables, graphs, code, data, citations, etc. If you are uncertain about the need to disclose the use of a particular tool, err on the side of caution, and include a disclosure in the acknowledgements section of the Work.
• If you are using generative AI software tools to edit and improve the quality of your existing text in much the same way you would use a typing assistant like Grammarly to improve spelling, grammar, punctuation, clarity, engagement or to use a basic word processing system to correct spelling or grammar, it is not necessary to disclose such usage of these tools in your Work.

Review and Publication Process

A double-anonymous review process will be employed for submissions to the main track. The submission must not reveal the identity of the authors in any way. Papers that violate the double-anonymous requirement will be desk-rejected. For more details on the double-anonymous process, please refer to FSE’s submission guidelines.

All submissions will be desk-checked to make sure that they are within the scope of the conference and have satisfied the submission requirements (e.g., page limits and anonymity).

Three members of the Program Committee will then be assigned to each submission for the review process. The Program Committee members can bid on submissions to review. The Program Committee will discuss the review results virtually and decide on the accepted submissions. The accepted submissions will be published in the ACM digital library.

AUTHORS TAKE NOTE: The official publication date is the date the proceedings are made available in the ACM Digital Library. This date may be up to two weeks prior to the first day of the conference. The official publication date affects the deadline for any patent filings related to published work.

ACM SIGSOFT Distinguished Paper Award (1 out of 25 accepted full papers)

• Is Artificial Intelligence an Elixir to the Software Engineering Community? An Empirical Study among Managers.
  Xin Zhao, Brian Vu, Sitesh Pattanaik

AIware Honorable Mention Paper Award

• Towards Migrating Neural Network Implementations
  Nadia Daoudi, Iván Alfonso, Jordi Cabot
• Fixpad++: Automated Bug Fix Verification using LLM Agents
  Mustafa Özkan İr, Mehmet Dedeler, Anil Koyuncu, Eray Tüzün
• An Empirical Study of Reasoning Steps in Thinking Code LLMs
  Haoran Xue, Gias Uddin, Song Wang
• Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Modernization
  Naing Oo Lwin, Rajesh Kumar
• Quality and Security Signals in AI-Generated Python Refactoring Pull Requests
  Mohamed Almukhtar, Anwar Ghammam, Hua Ming
• When AI Coding Assistants Leak Training Data: A Study of LLM Memorization in Code Generation
  Xiaoyu Cheng, Kundi Yao, Pengyu Nie, Weiyi Shang
• Testing AIware Systems: A Software Engineering Survey
  Karla Gonzalez, Mariam El Mezouar

AIware Distinguished Reviewer Award (8 out of 59 reviewers)

• Alex Bezzubov
• Jiho Shin
• Jieke Shi
• Luca Traini
• Md Shamimur Rahman
• Liang Peng
• Boyang Yang
• Italo Santos