Call for Submissions
We invite submissions of research and experience papers in two categories:
- Long paper: Long papers are research or experience papers describing research results, case studies, or insights from industry experience. A research or experience full paper is up to 10 pages plus a maximum of 2 pages for references.
- Short paper: Papers describing new challenges, new research results, visionary ideas, or experiences from, or in cooperation with, practitioners are welcome as short papers. In-progress research with interim results is also appropriate for a short paper. A short paper is up to 5 pages plus a maximum of 1 page for references.
When submitting, authors are asked to classify their papers as either research or experience papers. Please use the following guidance to determine the appropriate category:
-
Research Papers should primarily focus on research contributions, such as addressing a hypothesis, presenting novel methods, or offering theoretical insights. These papers contribute new findings to the field and advance the state of knowledge in software engineering for AI.
-
Experience Papers should emphasize insights from practical application, case studies, or collaboration with industry. These papers highlight lessons learned, real-world implementations, or actionable insights that benefit practitioners and the industry.
If you’re uncertain, consider whether the main contribution is advancing research knowledge (research paper) or practical understanding (experience paper).
The paper submissions will undergo a double-anonymous review process with three independent reviews and a virtual PC discussion. Acceptance criteria include contribution to the field of software engineering for AI, novelty, research and industrial relevance, soundness, and results. The accepted full and short papers will be published in the ICSE Companion proceedings.
If a paper is rejected as a long paper because the reviewers consider that the research is in the early stages or lacking evaluation, the paper will be reevaluated as a short paper. If accepted as a short paper, authors can choose to accept or decline to resubmit as a short paper. On another note, rejected papers may be considered for the poster track – this will depend on the quantity of papers received and if authors agree.
Scope and Topics of Interest
The area of interest for CAIN is Software Engineering for AI — improving the development of AI-based systems throughout the full life cycle. Topics include but are not limited to:
- System and software requirements and their relationship to AI/ML modeling.
- Data management ensuring relevance and efficiency related to business goals.
- System and software architecture for AI-enabled systems.
- Integration of AI and software development processes into the AI system development life cycle, including continuous integration and deployment, and system and software evolution.
- Ensuring and managing system and software nonfunctional properties and their relationship to AI/ML properties, including runtime properties such as performance, safety, security, and reliability; and life-cycle properties including reusability, maintainability and evolution.
- Collaboration, organizational, and management practices for a successful development of AI-enabled systems.
- Building effective infrastructures to support development of AI systems and components.
- Further clarifications on the CAIN Scope
Note: Submissions that report strictly on data science or model development without any connection to software engineering and AI-enabled systems will be desk-rejected. As stated earlier, there are many venues for those papers where authors would get much more valuable and relevant feedback.
Submission Form
Research and experience papers should be submitted to HotCrp. The submission deadline is firm, no extensions.
All submissions must adhere to the following requirements:
- Page limit is 10 pages plus 2 additional pages of references for long papers and 5 pages plus 1 additional page for references for short papers.
- Submissions must be unpublished original work and should not be under review or submitted elsewhere while being under consideration.
- By submitting to CAIN, authors acknowledge that they are aware of and agree to be bound by the ACM Policy and Procedures on Plagiarism and IEEE Plagiarism FAQ. The authors also acknowledge that they conform to the authorship policy of the ACM and the authorship policy of the IEEE.
- Paper review will employ a double-anonymous review process. Thus, no submission may reveal its authors’ identities. The authors must make every effort to honor the double-anonymous review process. In particular:
- Authors’ names must be omitted from the submitted paper.
- All references to the author’s prior work should be in the third person.
- Authors are encouraged to title their submission differently than preprints of the authors on ArXiV or similar sites. During review, authors should not publicly use the submission title.
Submissions must conform to the IEEE conference proceedings template, specified in the IEEE Conference Proceedings Formatting Guidelines (title in 24pt font and full text in 10pt type, LaTeX users must use \documentclass[10pt,conference]{IEEEtran}
without including the compsoc
or compsocconf
options).
Accepted papers will be published in the ICSE 2025 Co-located Event Proceedings and included in the IEEE and ACM Digital Libraries. Authors of accepted papers are required to register and present their accepted paper at the conference in order for the paper to be included in the proceedings and the Digital Libraries.
The official publication date is the date the proceedings are made available in the ACM or IEEE Digital Libraries. This date may be up to two weeks prior to the first day of ICSE 2025. The official publication date affects the deadline for any patent filings related to published work. Purchase of additional pages in the proceedings is not allowed.
Authors of papers receiving a Conditional Accept decision are expected to submit the revised papers with changes marked in a different color, such as using LaTeXdiff. The authors also need to submit an “Author Response” document capturing the authors’ response to each reviewer comment and how those comments were addressed in the revision. This is similar to the “Summary of Changes and Response” document that is typically submitted by authors for a journal paper major revision. The reviewers will check the revised paper against the original paper and the suggested changes. Conditional Accepts will be checked by only one member of the Program Committee, and this will be done in one pass.
Authors of rejected long papers may receive an acceptance as a short paper if the PC chairs and reviewers agree that it better meets the criteria for short papers. In this case, authors may decide to accept or reject the invitation if they would rather submit as a long paper to a different venue.
Similarly, authors of rejected long and short papers relevant to the field of AI Engineering may have their papers sent to a different CAIN track. Also in this case, authors may decide to accept or reject the invitation.
Accepted Papers
This program is tentative and subject to change.
Sun 27 AprDisplayed time zone: Eastern Time (US & Canada) change
07:00 - 19:00 | Ready Room SundayICSE Social, Networking and Special Rooms at 209 The Ready Room will be available throughout the week. There will be some tables with computers where people can edit presentations (bring on a USB stick) and upload presentations to the presentation rooms through the Contact 1 website. There will also be AV technicians to help if needed. You do not need to use the Ready Room: You have several choices: You can upload your presentation from your own computer in advance of your session (days in advance even) at the Contact 1 website (you will be sent a link). Or you can plug your computer in using an HDMI cable when you are starting your presentation. This last option is available but not recommended, since it increases the chance of delays. There will be some tables and couches in the Ready Room where you can get work done, or have small get-togethers with people. This room will not be ‘quiet’. If you want a quiet place to work or chill out (library quiet, no talking) then Room 209 will be available much of the time. The Ready Room will also have some poster boards. | ||
09:00 - 12:30 | Child Care Sunday AMICSE Social, Networking and Special Rooms at 102 Child Care Child Care at ICSE is free, but you must have registered for child care when you registered for the conference. If you need to add child care to your registration, please contact the registration desk. | ||
09:00 - 10:30 | Opening / Keynote 1Research and Experience Papers at 208 Chair(s): Grace Lewis Carnegie Mellon Software Engineering Institute | ||
09:00 30mDay opening | Opening Research and Experience Papers | ||
09:30 60mKeynote | Is Prompt Engineering? Research and Experience Papers Jeremy Barnes ServiceNow |
10:30 - 11:00 | |||
10:30 30mCoffee break | Sunday Morning Break ICSE Catering |
12:30 - 14:00 | |||
12:30 90mLunch | Sunday Lunch ICSE Catering |
14:00 - 15:30 | Architecting and Testing AI SystemsResearch and Experience Papers at 208 Chair(s): Jan-Philipp Steghöfer XITASO GmbH IT & Software Solutions | ||
14:00 15mTalk | How Do Model Export Formats Impact the Development of ML-Enabled Systems? A Case Study on Model IntegrationDistinguished paper Award Candidate Research and Experience Papers Shreyas Kumar Parida ETH Zurich, Ilias Gerostathopoulos Vrije Universiteit Amsterdam, Justus Bogner Vrije Universiteit Amsterdam Pre-print | ||
14:15 15mTalk | RAGProbe: Breaking RAG Pipelines with Evaluation ScenariosDistinguished paper Award Candidate Research and Experience Papers Shangeetha Sivasothy Applied Artificial Intelligence Institute, Deakin University, Scott Barnett Deakin University, Australia, Stefanus Kurniawan Deakin University, Zafaryab Rasool Applied Artificial Intelligence Institute, Deakin University, Rajesh Vasa Deakin University, Australia | ||
14:30 15mTalk | On-Device or Remote? On the Energy Efficiency of Fetching LLM-Generated Content Research and Experience Papers Vince Nguyen Vrije Universiteit Amsterdam, Hieu Huynh Vrije Universiteit Amsterdam, Vidya Dhopate Vrije Universiteit Amsterdam, Anusha Annengala Vrije Universiteit Amsterdam, Hiba Bouhlal Vrije Universiteit Amsterdam, Gian Luca Scoccia Gran Sasso Science Institute, Matias Martinez Universitat Politècnica de Catalunya (UPC), Vincenzo Stoico Vrije Universiteit Amsterdam, Ivano Malavolta Vrije Universiteit Amsterdam Pre-print | ||
14:45 10mTalk | LoCoML: A Framework for Real-World ML Inference Pipelines Research and Experience Papers Kritin Maddireddy IIIT Hyderabad, Santhosh Kotekal Methukula IIIT Hyderabad, Chandrasekar S IIIT Hyderabad, Karthik Vaidhyanathan IIIT Hyderabad | ||
14:55 10mTalk | Towards Continuous Experiment-driven MLOps Research and Experience Papers Keerthiga Rajenthiram Vrije Universiteit Amsterdam, Milad Abdullah Charles University, Ilias Gerostathopoulos Vrije Universiteit Amsterdam, Petr Hnětynka Charles University, Tomas Bures Charles University, Czech Republic, Gerard Pons Universitat Politècnica de Catalunya, Barcelona, Spain, Besim Bilalli Universitat Politècnica de Catalunya, Barcelona, Spain, Anna Queralt Universitat Politècnica de Catalunya, Barcelona, Spain | ||
15:05 25mOther | Discussion Research and Experience Papers |
15:30 - 16:00 | |||
15:30 30mBreak | Sunday Afternoon Break ICSE Catering |
Mon 28 AprDisplayed time zone: Eastern Time (US & Canada) change
07:00 - 19:00 | Ready Room MondayICSE Social, Networking and Special Rooms at 209 The Ready Room will be available throughout the week. There will be some tables with computers where people can edit presentations (bring on a USB stick) and upload presentations to the presentation rooms through the Contact 1 website. There will also be AV technicians to help if needed. You do not need to use the Ready Room: You have several choices: You can upload your presentation from your own computer in advance of your session (days in advance even) at the Contact 1 website (you will be sent a link). Or you can plug your computer in using an HDMI cable when you are starting your presentation. This last option is available but not recommended, since it increases the chance of delays. There will be some tables and couches in the Ready Room where you can get work done, or have small get-togethers with people. This room will not be ‘quiet’. If you want a quiet place to work or chill out (library quiet, no talking) then Room 209 will be available much of the time. The Ready Room will also have some poster boards. | ||
09:00 - 10:30 | |||
09:00 - 10:00 | Keynote 2Research and Experience Papers at 208 Chair(s): Henry Muccini University of L'Aquila, Italy | ||
09:00 60mKeynote | Beyond Machine Learning and Foundation Models: A Research Roadmap for Multi-Paradigm AI Engineering Research and Experience Papers Marcos Kalinowski Pontifical Catholic University of Rio de Janeiro (PUC-Rio) |
10:30 - 11:00 | |||
10:30 - 11:00 | |||
10:30 30mBreak | Monday Morning Break ICSE Catering |
11:00 - 12:30 | |||
11:00 - 12:30 | |||
11:00 20mTalk | Optimizing Data Analytics Workflows through User-driven Experimentation: Progress and Updates Doctoral Symposium Keerthiga Rajenthiram Vrije Universiteit Amsterdam | ||
11:20 20mTalk | CoCo Challenges in ML Engineering Teams: How to Collaboratively Build ML-Enabled Systems Doctoral Symposium Aidin Azamnouri Technical University of Munich | ||
11:40 20mTalk | Towards a Privacy-by-Design Framework for ML-Enabled Systems Doctoral Symposium Yorick Sens Ruhr University Bochum | ||
12:00 20mTalk | Towards an Adoption Framework to Foster Trust in AI-Assisted Software Engineering Doctoral Symposium Marvin Muñoz Barón University of Stuttgart |
12:30 - 13:00 | |||
12:30 - 14:00 | |||
12:30 90mLunch | Monday Lunch ICSE Catering |
14:00 - 15:30 | |||
14:00 - 15:30 | Quality Assurance for AI systemsResearch and Experience Papers at 208 Chair(s): Eduardo Santana de Almeida Federal University of Bahia | ||
14:00 10mTalk | Towards a Domain-Specific Modeling Language for Streamlined Change Management in AI Systems Development Research and Experience Papers Razan Abualsaud IRIT, CNRS, Toulouse | ||
14:10 15mTalk | An AI-driven Requirements Engineering Framework Tailored for Evaluating AI-Based Software Research and Experience Papers Hamed Barzamini , Fatemeh Nazaritiji Northern Illinois University, Annalise Brockmann Northern Illinois University, Hasan Ferdowsi Northern Illinois university, Mona Rahimi Northern Illinois University | ||
14:25 15mTalk | MLScent: A tool for Anti-pattern detection in ML projects Research and Experience Papers | ||
14:40 15mTalk | Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)Distinguished paper Award Candidate Research and Experience Papers Boyue Caroline Hu University of Toronto, Divya Gopinath KBR; NASA Ames, Ravi Mangal Colorado State University, Nina Narodytska VMware Research, Corina S. Păsăreanu Carnegie Mellon University, Susmit Jha SRI | ||
14:55 15mTalk | Investigating Issues that Lead to Code Technical Debt in Machine Learning Systems Research and Experience Papers Rodrigo Ximenes Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Antonio Pedro Santos Alves Pontifical Catholic University of Rio de Janeiro, Tatiana Escovedo Pontifical Catholic University of Rio de Janeiro, Rodrigo Spinola Virginia Commonwealth University, Marcos Kalinowski Pontifical Catholic University of Rio de Janeiro (PUC-Rio) | ||
15:10 10mTalk | Addressing Quality Challenges in Deep Learning: The Role of MLOps and Domain Knowledge Research and Experience Papers Santiago del Rey Universitat Politècnica De Catalunya - Barcelona Tech, Adrià Medina Universitat Politècnica de Barcelona - BarcelonaTech (UPC), Xavier Franch Universitat Politècnica de Catalunya, Silverio Martínez-Fernández UPC-BarcelonaTech Pre-print | ||
15:20 10mOther | Discussion Research and Experience Papers |
14:00 - 15:30 | |||
14:00 20mTalk | Architectures to Embrace Change for Trustworthy AI-based Systems Doctoral Symposium Merel Veracx Fontys University of Applied Sciences | ||
14:20 20mTalk | Assessing and Enhancing the Robustness of LLM-based Multi-Agent Systems Through Chaos Engineering. Doctoral Symposium Joshua Segun Owotogbe JADS/Tilburg University | ||
14:40 20mTalk | Designing ML-Enabled Software Systems with ML Model Composition: A Green AI Perspective Doctoral Symposium Rumbidzai Chitakunye Vrije Universiteit Amsterdam | ||
15:00 20mTalk | A Metrics-Oriented Architectural Model to Characterize Complexity on Machine Learning-Enabled Systems Doctoral Symposium Renato Cordeiro Ferreira University of São Paulo |
15:30 - 16:00 | |||
15:30 30mBreak | Monday Afternoon Break ICSE Catering |
16:00 - 17:30 | |||
16:00 - 17:30 | |||
16:00 15mTalk | DDPT: Diffusion Driven Prompt Tuning for Large Language Model Code Generation Research and Experience Papers Jinyang Li The University of Adelaide, Sangwon Hyun CREST, University of Adelaide, Muhammad Ali Babar School of Computer Science, The University of Adelaide | ||
16:15 15mTalk | Engineering LLM Powered Multi-agent Framework for Autonomous CloudOpsDistinguished paper Award Candidate Research and Experience Papers Kannan Parthasarathy MontyCloud, Karthik Vaidhyanathan IIIT Hyderabad, Rudra Dhar SERC, IIIT Hyderabad, India, Venkat Krishnamachari MontyCloud, Adyansh Kakran International Institute of Information Technology, Hyderabad, Sreemaee Akshathala IIIT Hyderabad, Shrikara Arun IIIT Hyderabad, Amey Karan IIIT Hyderabad, Basil Muhammed MontyCloud, Sumant Dubey MontyCloud, Mohan Veerubhotla MontyCloud | ||
16:30 15mTalk | Generating and Verifying Synthetic Datasets with Requirements Engineering Research and Experience Papers Lynn Vonderhaar Embry-Riddle Aeronautical University, Timothy Elvira Embry-Riddle Aeronautical University, Omar Ochoa Embry-Riddle Aeronautical University | ||
16:45 15mTalk | LLM-Based Safety Case Generation for Baidu Apollo: Are We There Yet? Research and Experience Papers | ||
17:00 12mTalk | SqPal - text to SQL GenAI tool for PayPal Industry Talks | ||
17:12 18mOther | Discussion Research and Experience Papers |
16:00 - 17:30 | |||
16:00 20mTalk | Identification and Optimization of Redundant Code Using Large Language Models Doctoral Symposium Shamse Tasnim Cynthia University of Saskatchewan | ||
16:20 20mTalk | Systematic Testing of Security-Related Defects in LLM-Based Applications Doctoral Symposium Hasan Kaplan Jheronimus Academy of Data Science, Tilburg University | ||
16:40 20mTalk | Model-Based Verification for AI-Enabled Cyber-Physical Systems through Guided Falsification of Temporal Logic Properties Doctoral Symposium Hadiza Yusuf University of Michigan - Dearborn |
Papers - Accepted
Long Papers
Rule-Based Assessment of Reinforcement Learning Practices Using Large Language Models
Evangelos Ntentos, Stephen John Warnett, Uwe Zdun
DDPT: Diffusion Driven Prompt Tuning for Large Language Model Code Generation
Authors: Jinyang Li, Sangwon Hyun, M. Ali Babar
Themes of Building LLM-based Applications for Production: A Practitioner’s View
Authors: Alina Mailach ; Sebastian Simon; Johannes Dorn, Norbert Siegmund
An AI-driven Requirements Engineering Framework Tailored for Evaluating AI-Based Software
Authors: Hamed Barzamini, Fatemeh Nazaritiji, Annalise Brockmann ; Hasan Ferdowsi; Mona Rahimi
How Do Model Export Formats Impact the Development of ML-Enabled Systems? A Case Study on Model Integration
Authors: Shreyas Kumar Parida; Ilias Gerostathopoulos, Justus Bogner
ImageBiTe: A Framework for Evaluating Representational Harms in Text-to-Image Models
Authors: Sergio Morales, Robert Clarisó; Jordi Cabot
MLScent: A tool for Anti-pattern detection in ML projects
Authors: Karthik Shivashankar, Antonio Martini
Generating and Verifying Synthetic Datasets with Requirements Engineering
Authors: Lynn Vonderhaar, Timothy Elvira, Omar Ochoa
RAGProbe: Breaking RAG Pipelines with Evaluation Scenarios
Authors: Shangeetha Sivasothy, Scott Barnett, Stefanus Kurniawan, Zafaryab Rasool, Rajesh Vasa
On-Device or Remote? On the Energy Efficiency of Fetching LLM-Generated Content
Authors: Vince Nguyen, Hieu Huynh, Vidya Dhopate, Anusha Annengala, Hiba Bouhlal; Gian Luca Scoccia; Matias Martinez; Vincenzo Stoico; Ivano Malavolta
Debugging and Runtime Analysis of Neural Networks with VLMs
Authors: Boyue Caroline Hu; Divya Gopinath; Ravi Mangal; Nina Narodytska; Corina Pasareanu; Susmit Jha
Bringing Machine Learning Models Beyond the Experimental Stage with Explainable AI
Authors: Niels With Mikkelsen, Lasse Pedersen, Mansoor Hussain; Victor Foged; Ekkart Kindler
InsightAI: Root Cause Analysis in Large Hierarchical Log Files with Private Data Using Large Language Models
Authors: Maryam Ekhlasi; Anurag Prakash; Michel Dagenais; Maxime Lamothe
Investigating Issues that Lead to Code Technical Debt in Machine Learning Systems
Authors: Rodrigo Ximenes, Antonio Pedro Santos Alves, Tatiana Escovedo; Rodrigo Spinola; Marcos Kalinowski
Engineering LLM Powered Multi-agent Framework for Autonomous CloudOps
Authors: Kannan Parthasarathy; Karthik Vaidhyanathan, Rudra Dhar; Venkat Krishnamachari; Adyansh Kakran; Sreemaee Akshathala, Shrikara Arun, Amey Karan ; Basil Muhammed, Sumant Dubey, Mohan Veerubhotla
LLM-Based Safety Case Generation for Baidu Apollo: Are We There Yet?
Authors: Oluwafemi Odu, Alvine B. Belle, Song Wang
Short Papers
Designing and implementing LLM guardrails components in production environments
Authors: Mateus Devino, Evaline Ju, Paulo Marques Caldeira Junior
Towards a Domain-Specific Modeling Language for Streamlined Change Management in AI Systems Development
Authors: Razan abualsaud
Approach Towards Semi-Automated Certification of Low Criticality ML-Enabled Airborne Applications
Authors: Chandrasekar Sridhar, Vyakhya Gupta, Prakhar Jain, Karthik Vaidhyanathan
From Hazard Identification to Control Design: Proactive and AI-Supported Safety Engineering for ML-powered Systems
Authors: Yining Hong, Christopher Timperley, Christian Kaestner
Developing Multi-Agent LLM Applications through Continuous Human-LLM Co-Programming
Authors: Hui Song, Arda Goknil; Xiaojun Jiang, Espen Melum; Hyunwhan Joe; Caterina Gazzotti; Valerio Frascolla; Adela Nedisan Videsjorden, Phu Nguyen
LoCoML: A Framework for Real-World ML Inference Pipelines
Authors: Kritin Maddireddy, Santhosh Kotekal Methukula, Chandrasekar Sridhar, Karthik Vaidhyanathan
Addressing Quality Challenges in Deep Learning: The Role of MLOps and Domain Knowledge
Authors: Santiago del Rey, Adrià Medina; Xavier Franch; Silverio Martínez-Fernández
Towards Continuous Experiment-driven MLOps
Authors: Keerthiga Rajenthiram; Milad Abdullah; Ilias Gerostathopoulos; Petr Hnetynka, Tomas Bures; Gerard Pons, Besim Bilalli, Anna Queralt