FORGE 2025
Sun 27 - Mon 28 April 2025 Ottawa, Ontario, Canada
co-located with ICSE 2025

The 2nd ACM international conference on AI Foundation Models and Software Engineering (FORGE 2025) in ICSE 2025 aims to bring researchers, practitioners, and educators from the AI and Software Engineering community to solve the new challenges that we meet in the era of foundation models.

Foundation models (e.g., ChatGPT and Llama) have attracted great attention from both academia and industry. In Software Engineering, several studies showed that Large-Language Models (LLMs) achieved remarkable performance in various tasks, including code generation, testing, code review, and program repair. Recently, many LLM-based development tools have been released to improve software development and show great potential, such as GitHub Copilot and Amazon CodeWhisperer.

FORGE 2025 will be held on Sun 27 - Mon 28 April 2025, in Ottawa, Ontario, Canada.

Dates
Sun 27 Apr 2025
Mon 28 Apr 2025
Plenary
Hide plenary sessions

This program is tentative and subject to change.

You're viewing the program in a time zone which is different from your device's time zone change time zone

Sun 27 Apr

Displayed 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
FORGE2025 Opening / KeynoteKeynotes at 207
09:00
10m
Day opening
Introduction from The Chairs
Keynotes

09:10
60m
Keynote
Keynote
Keynotes
Prem Devanbu University of California at Davis
10:30 - 11:00
10:30
30m
Coffee break
Sunday Morning Break
ICSE Catering

11:00 - 12:30
FORGE2025 Panel / KeynoteKeynotes / at 207
11:00
60m
Keynote
Keynote
Keynotes
Graham Neubig Carnegie Mellon University
12:00
30m
Panel
Panel Discussion
Panel

12:30 - 14:00
12:30
90m
Lunch
Sunday Lunch
ICSE Catering

13:30 - 14:00
14:00 - 15:30
Session1: FM for Code Generation Research Papers / Data and Benchmarking at 207
14:00
12m
Long-paper
RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion
Research Papers
Huy Nhat Phan FPT Software AI Center, Hoang Nhat Phan Nanyang Technological University, Tien N. Nguyen University of Texas at Dallas, Nghi D. Q. Bui Salesforce Research
14:12
12m
Long-paper
SoTaNa: An Open-Source Software Engineering Instruction-Tuned Model
Research Papers
Ensheng Shi Xi’an Jiaotong University, Yanlin Wang Sun Yat-sen University, Fengji Zhang Microsoft Research Asia, Bei Chen Microsoft Research Asia, Hongyu Zhang Chongqing University, yanli wang Sun Yat-sen University, Daya Guo Sun Yat-sen University, Lun Du Microsoft Research, Shi Han Microsoft Research, Dongmei Zhang Microsoft Research, Hongbin Sun Xi’an Jiaotong University
14:24
12m
Long-paper
Automated Codebase Reconciliation using Large Language Models
Research Papers
Aneri Gandhi University of Toronto, Sanjukta De Advanced Micro Devices, Marsha Chechik University of Toronto, Vinay Pandit Advanced Micro Devices, Max Kiehn Advanced Micro Devices, Matthieu Chan Chee Advanced Micro Devices, Yonas Bedasso Advanced Micro Devices
14:36
12m
Long-paper
AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code
Research Papers
Lola Solovyeva University of Twente, Sophie Weidmann University of Twente, Fernando Castor University of Twente
14:48
6m
Short-paper
SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation
Data and Benchmarking
14:54
6m
Short-paper
SE Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering
Research Papers
Zhimin Zhao Queen's University
15:00
12m
Long-paper
PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
Research Papers
Yun Peng The Chinese University of Hong Kong, Akhilesh Deepak Gotmare Salesforce Research, Michael Lyu The Chinese University of Hong Kong, Caiming Xiong Salesforce Research, Silvio Savarese Salesforce Research, Doyen Sahoo Salesforce Research
15:12
6m
Short-paper
HyRACC: A Hybrid Retrieval-Augmented Framework for More Efficient Code Completion
Research Papers
Chuanyi Li Nanjing University, Jiwei Shang Nanjing University, Yi Feng Nanjing University, Bin Luo Nanjing University
15:18
6m
Short-paper
OptCodeTrans: Boost LLMs on Low-Resource Programming Language Translation
Research Papers
Jianbo Lin Nanjing University, Yi Shen Nanjing University, Chuanyi Li Nanjing University, Changan Niu Software Institute, Nanjing University, Bin Luo Nanjing University
15:30 - 16:00
15:30
30m
Break
Sunday Afternoon Break
ICSE Catering

16:00 - 17:30
Session2: FM for Software Quality Assurance & TestingResearch Papers / Data and Benchmarking at 207
16:00
12m
Long-paper
Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements
Research Papers
Seyed Moein Abtahi Ontario Tech University, Akramul Azim Ontario Tech University
16:12
12m
Long-paper
Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models
Research Papers
Marc Bruni University of Applied Sciences and Arts Northwestern Switzerland, Fabio Gabrielli University of Applied Sciences and Arts Northwestern Switzerland, Mohammad Ghafari TU Clausthal, Martin Kropp University of Applied Sciences and Arts Northwestern Switzerland
Pre-print
16:24
12m
Long-paper
Vulnerability-Triggering Test Case Generation from Third-Party Libraries
Research Papers
Yi Gao Zhejiang University, Xing Hu Zhejiang University, Zirui Chen , Tongtong Xu Nanjing University, Xiaohu Yang Zhejiang University
16:36
6m
Short-paper
Microservices Performance Testing with Causality-enhanced Large Language Models
Research Papers
Cristian Mascia University of Naples Federico II, Roberto Pietrantuono Università di Napoli Federico II, Antonio Guerriero Università di Napoli Federico II, Luca Giamattei Università di Napoli Federico II, Stefano Russo Università di Napoli Federico II
16:42
6m
Short-paper
MaRV: A Manually Validated Refactoring Dataset
Data and Benchmarking
Henrique Gomes Nunes Universidade Federal de Minas Gerais, Tushar Sharma Dalhousie University, Eduardo Figueiredo Federal University of Minas Gerais
16:48
6m
Short-paper
PyResBugs: A Dataset of Residual Python Bugs for Natural Language-Driven Fault Injection
Data and Benchmarking
Domenico Cotroneo University of Naples Federico II, Giuseppe De Rosa University of Naples Federico II, Pietro Liguori University of Naples Federico II
16:54
6m
Short-paper
The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models
Data and Benchmarking
Jonathan Katzy Delft University of Technology, Răzvan Mihai Popescu Delft University of Technology, Arie van Deursen TU Delft, Maliheh Izadi Delft University of Technology
17:00
12m
Long-paper
ELDetector: An Automated Approach Detecting Endless-loop in Mini Programs
Research Papers
Nan Hu Xi’an Jiaotong University, Ming Fan Xi'an Jiaotong University, Jingyi Lei Xi'an Jiaotong University, Jiaying He Xi'an Jiaotong University, Zhe Hou China Mobile System Integration Co.
17:12
12m
Long-paper
Testing Android Third Party Libraries with LLMs to Detect Incompatible APIs
Research Papers
Tarek Mahmud Texas State University, bin duan University of Queensland, Meiru Che Central Queensland University, Anne Ngu Texas State University, Guowei Yang University of Queensland

Mon 28 Apr

Displayed 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 - 10:30
FORGE2025 Keynote & Session3: Collaborative Software DevelopmentKeynotes / Research Papers at 207
09:00
60m
Keynote
Keynote: Trust No Bot? Forging Confidence in AI for Software Engineering
Keynotes
Thomas Zimmermann University of California, Irvine
10:00
12m
Long-paper
AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
Research Papers
Minh Nguyen Huynh FPT Software AI Center, Thang Phan Chau FPT Software AI Center, Phong X. Nguyen FPT Software AI Center, Nghi D. Q. Bui Salesforce Research
10:12
12m
Long-paper
Enhancing Pull Request Reviews: Leveraging Large Language Models to Detect Inconsistencies Between Issues and Pull Requests
Research Papers
Ali Tunahan Işık Bilkent University, Hatice Kübra Çağlar Bilkent University, Eray Tüzün Bilkent University
10:30 - 11:00
10:30
30m
Break
Monday Morning Break
ICSE Catering

11:00 - 12:30
11:00 - 12:30
Session4: Human-AI Collaboration & Legal Aspects of using FMResearch Papers / Industry Papers at 207
11:00
12m
Long-paper
Extracting Fix Ingredients using Language Models
Research Papers
Julian Prenner Free University of Bozen-Bolzano, Romain Robbes Univ. Bordeaux, CRNS
11:12
12m
Long-paper
CodeFlow: Program Behavior Prediction with Dynamic Dependencies Learning
Research Papers
Cuong Chi Le FPT Software AI Center, Hoang Nhat Phan Nanyang Technological University, Huy Nhat Phan FPT Software AI Center, Tien N. Nguyen University of Texas at Dallas, Nghi D. Q. Bui Salesforce Research
11:24
12m
Long-paper
Addressing Specific and Complex Scenarios in Semantic Parsing
Research Papers
Yu Wang Nanjing University, Ming Fan Xi'an Jiaotong University, Ting Liu Xi'an Jiaotong University
11:36
12m
Long-paper
Skill over Scale: The Case for Medium, Domain-Specific Models for SE
Research Papers
Manisha Mukherjee Carnegie Mellon University, Vincent J. Hellendoorn Carnegie Mellon University
Pre-print
11:48
12m
Long-paper
Resource-Efficient & Effective Code Summarization
Research Papers
Saima Afrin William & Mary, Joseph Call William & Mary, Khai Nguyen William & Mary, Oscar Chaparro William & Mary, Antonio Mastropaolo William and Mary, USA
12:00
6m
Short-paper
How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering
Research Papers
Christoph Treude Singapore Management University, Marco Gerosa Northern Arizona University
Pre-print
12:06
6m
Short-paper
"So what if I used GenAI?” - Legal Implications of Using GenAI in Software Engineering Research
Research Papers
Gouri Ginde (Deshpande) University of Calgary
12:12
6m
Short-paper
Evaluating the Ability of GPT-4o to Generate Verifiable Specifications in VeriFast
Research Papers
Marilyn Rego Purdue University, Wen Fan Purdue University, Xin Hu Univeristy of Michigan - Ann Arbor, Sanya Dod , Zhaorui Ni Purdue University, Danning Xie Purdue University, Jenna DiVincenzo (Wise) Purdue University, Lin Tan Purdue University
12:18
6m
Short-paper
Towards Generating App Feature Descriptions Automatically with LLMs: the Setapp Case Study
Industry Papers
12:30 - 14:00
12:30
90m
Lunch
Monday Lunch
ICSE Catering

14:00 - 15:30
14:00 - 15:30
FORGE2025 KeynoteKeynotes at 207
14:00
45m
Keynote
Industry Keynote
Keynotes
Dong Qiu Huawei Technologies
14:45
45m
Keynote
Industry Keynote
Keynotes
Darya Rovdo JetBrains
15:30 - 16:00
15:30
30m
Break
Monday Afternoon Break
ICSE Catering

16:00 - 17:30
16:00 - 17:30
FORGE2025 Tutorial & Session5: FM EvaluationKeynotes / Tutorials / Research Papers at 207
16:00
12m
Long-paper
Cyber-Attack Detection and Localization for SCADA system of CPSs
Research Papers
Dan Li Sun Yat-sen University, Junnan Tang Sun Yat-Sen University, Shunyu Wu Sun Yat-Sen University, Zibin Zheng Sun Yat-sen University, See-Kiong Ng National University of Singapore
16:12
12m
Long-paper
A Comprehensive Study of Bug Characteristics on Foundation Language Models
Research Papers
Junxiao Han , Guanqi Wang Zhejiang University, Jiakun Liu Singapore Management University, Lingfeng Bao Zhejiang University, Xing Hu Zhejiang University, Jinling Wei Hangzhou City University, Shuiguang Deng Zhejiang University; Alibaba-Zhejiang University Joint Institute of Frontier Technologies
16:24
12m
Long-paper
Testing Refactoring Engine via Historical Bug Report driven LLM
Research Papers
Haibo Wang , Zhuolin Xu Concordia University, Shin Hwei Tan Concordia University
Pre-print
16:36
45m
Tutorial
Beyond Code Generation: Evaluating and Improving LLMs for Code Intelligence
Tutorials
Fatemeh Hendijani Fard University of British Columbia
17:21
9m
Keynote
Industry Keynote 3
Keynotes

Accepted Papers

Title
A Comprehensive Study of Bug Characteristics on Foundation Language Models
Research Papers
Addressing Specific and Complex Scenarios in Semantic Parsing
Research Papers
AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
Research Papers
AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code
Research Papers
Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements
Research Papers
Automated Codebase Reconciliation using Large Language Models
Research Papers
Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models
Research Papers
Pre-print
CodeFlow: Program Behavior Prediction with Dynamic Dependencies Learning
Research Papers
Cyber-Attack Detection and Localization for SCADA system of CPSs
Research Papers
ELDetector: An Automated Approach Detecting Endless-loop in Mini Programs
Research Papers
Enhancing Pull Request Reviews: Leveraging Large Language Models to Detect Inconsistencies Between Issues and Pull Requests
Research Papers
Evaluating the Ability of GPT-4o to Generate Verifiable Specifications in VeriFast
Research Papers
Extracting Fix Ingredients using Language Models
Research Papers
How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering
Research Papers
Pre-print
HyRACC: A Hybrid Retrieval-Augmented Framework for More Efficient Code Completion
Research Papers
Microservices Performance Testing with Causality-enhanced Large Language Models
Research Papers
OptCodeTrans: Boost LLMs on Low-Resource Programming Language Translation
Research Papers
PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
Research Papers
RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion
Research Papers
Resource-Efficient & Effective Code Summarization
Research Papers
SE Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering
Research Papers
Skill over Scale: The Case for Medium, Domain-Specific Models for SE
Research Papers
Pre-print
SoTaNa: An Open-Source Software Engineering Instruction-Tuned Model
Research Papers
"So what if I used GenAI?” - Legal Implications of Using GenAI in Software Engineering Research
Research Papers
Testing Android Third Party Libraries with LLMs to Detect Incompatible APIs
Research Papers
Testing Refactoring Engine via Historical Bug Report driven LLM
Research Papers
Pre-print
Vulnerability-Triggering Test Case Generation from Third-Party Libraries
Research Papers

Call for Papers

The 2nd ACM international conference on AI Foundation Models and Software Engineering (FORGE 2025) in ICSE 2025 aims to bring researchers, practitioners, and educators from the AI and Software Engineering community to solve the new challenges that we meet in the era of foundation models.

Foundation models (e.g., ChatGPT and Llama) have attracted great attention from both academia and industry. In Software Engineering, several studies showed that Large-Language Models (LLMs) achieved remarkable performance in various tasks, including code generation, testing, code review, and program repair. Recently, many LLM-based development tools have been released to improve software development and show great potential, for example, GitHub Copilot and Amazon CodeWhisperer.

FORGE 2025 will be held on Sun 27 - Mon 28 April 2025, in Ottawa, Ontario, Canada.

Topic of Interests

We solicit submissions describing original and unpublished results of theoretical, empirical, conceptual, and experimental software engineering research related to Software Engineering with Foundation Models. Topics of interest include but are not limited to:

  1. FM for Requirement Engineering and Software Design
  2. FM for Code Generation/Reuse
  3. FM for Software Quality Assurance (e.g., including code review, analysis, testing, and debugging)
  4. FM to support software evolution (e.g., refactoring, technical debt management)
  5. FM for Software Security and Privacy
  6. FM for AIOps
  7. FM for software supply chain management, e.g., FM-based vulnerability identification, software composition analysis
  8. LLM Agents for SE tasks, e.g., how to use various FMs (e.g., LangChain) to complete a SE task.
  9. Prompt Engineering for Software Development
  10. Legal Aspects of using FM

Note that the aforementioned topics may not be limited to FM, but may also refer to new technology based on how AI models evolve.

Awards

The best papers will be awarded with an ACM SIGSOFT Distinguished Paper Award at FORGE. A selection of the best papers will be invited to a Special Issue of Empirical Software Engineering (EMSE).

How to Submit

We accept both full and new idea papers:

  1. Full Papers are expected to present new techniques, and/or provide research results, and/or report industry/open-source practice when applying foundation models for SE, and should be evaluated in a scientific way. Full Paper must not exceed 10 pages for the main text, inclusive of all figures, tables, appendices, etc. Two more pages containing only references are permitted.
  2. New Idea Papers should present new ideas in the field, e.g., new directions or techniques that are not yet fully developed and/or evaluated, or visions that show the future of AI foundation models and SE. Accepted new idea papers will present their ideas in a short lightning talk. New Idea Paper must not exceed 4 pages for the main text, inclusive of all figures, tables, appendices, etc. Two more pages containing only references are permitted.

All submissions must be in PDF. The page limit is strict, and it will not be possible to purchase additional pages at any point in the process (including after acceptance).

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).

Note, we use double-anonymous reviewing. Be sure to remove the list of authors from the submitted paper. If citing your own prior work, please do so in the third person to obscure the relationship you have with it. For advice, guidance, and explanation about the double-anonymous review process, see ICSE Research Track’s Q&A page.

All papers must be written in English. The authors are strongly encouraged to use the HotCRP format checker on their submissions. Note that the format checker is not perfect. In particular, it can complain about small fonts in figures, footnotes, or references. As long as the main text follows the requested format, and the figures are readable, the paper will not be rejected for format violations. If you have any concerns, please contact the program chairs.

All papers should be made accessible to people with disabilities. Some guidelines from the SIGACCESS community are available here: https://assets21.sigaccess.org/creating_accessible_pdfs.html.

Please submit your paper on HotCRP: https://forge2025.hotcrp.com/.

Review Criteria

Following the review criteria of ICSE 2025, each paper submitted to the FORGE 2025 will be evaluated based on the following criteria:

  1. Novelty: The novelty and innovativeness of contributed solutions, problem formulations, methodologies, theories, and/or evaluations, i.e., the extent to which the paper is sufficiently original with respect to the state-of-the-art.
  2. Rigor: The soundness, clarity, and depth of a technical or theoretical contribution, and the level of thoroughness and completeness of an evaluation.
  3. Relevance: The significance and/or potential impact of the research on the field of software engineering.
  4. Verifiability and Transparency: The extent to which the paper includes sufficient information to understand how an innovation works; to understand how data was obtained, analyzed, and interpreted; and how the paper supports independent verification or replication of the paper’s claimed contributions. Any artifacts attached to or linked from the paper will be checked by one reviewer.
  5. Presentation: The clarity of the exposition in the paper.

Reviewers will carefully consider all of the above criteria during the review process, and authors should take great care in clearly addressing them all. The paper should clearly explain and justify the claimed contributions. Each paper will be handled by an area chair who will ensure reviewing consistency among papers submitted within that area.

:
: