Industry Challenge TrackICSE 2026

The Industry Challenge Track is the premier venue for practitioners and researchers to present industry challenges in the software engineering domain and their associated solutions. The community is expected to discuss insights, innovations, and solutions to software engineering challenges in practice.

Given that addressing software engineering challenges in the industry relies on excellent software engineering research, the Industry Challenge Track provides a unique forum for networking, exchanging ideas, fostering innovations, and forging long-term collaborations to address such challenges from the industry. It is expected to become a prestigious forum for researchers and practitioners to meet and present industry-relevant research results in software engineering.

The Industry Challenge Track will welcome participants and speakers from both academic and industrial sectors, drawing together researchers and practitioners for discussions on research directions to address existing challenges. The track will be composed of invited talks, challenge presentations, paper (for solutions) presentations, and interactive sessions, all with a strong focus on software engineering industry challenges. Please note that the Industry Challenge Track uses a double-anonymous submission policy.

Process Overview

1. Challenge Proposal Submission by Industry (by July 17th, 2025)
   Companies are invited to submit a 1-page description of real-world software engineering challenges they face. These should be concrete, non-trivial problems that could benefit from innovative academic or industrial solutions. Further details are provided below.

2. Selection of Challenges (by July 24th, 2025) The Industry Challenge Track Co-Chairs will evaluate the submitted challenges and select those deemed most relevant, impactful, and suitable for the ICSE audience.

3. Challenge Dissemination (by July 31st, 2025) The selected challenges will be publicly announced and shared with the broader software engineering community, inviting researchers and practitioners to address them.

4. Submission of Solution Papers (by November 07th, 2025) Interested participants are encouraged to submit a Solution Paper addressing one of the selected challenges. Submissions must demonstrate technical soundness, relevance to the challenge, and potential for impact. More details on the Call for Papers.

5. Evaluation of Solutions (notification sent by December 22nd, 2025) Submitted Solution Papers will be reviewed by a dedicated Program Committee (PC) that includes both academic and industry experts, including representatives from the originating companies. The committee will select the most significant and compelling solutions for presentation and recommend potential distinguished Solution Papers for an award. The distinguished Solution Paper will be officially awarded during the ICSE 2026 main conference, and the authors will receive a prize amounting to between US$1,000 and US$5,000.

6. Presentation of Challenges and Solutions (during the ICSE 2026 main conference)
   At ICSE 2026, each selected company will present its challenge in a dedicated session open to all attendees. This will be followed by presentations of the corresponding selected Solution Papers, providing a dynamic forum for dialogue, feedback, and collaboration between industry and academia.

Key dates:

• Submission of Industry Challenges: by July 17th, 2025, AoE
• Challenges Dissemination: by July 31st, 2025, AoE
• Submission of Solution Papers: by Nov. 07th 2025, AoE
• Notification of Accepted Solution papers: Dec 22nd 2025, AoE
• Presentation of challenges and solutions at ICSE 2026: April 15-17, 2026

Call for Papers

Submission of Challenge Papers

Challenge papers are a 1-pager description of a practical, concrete, and non-trivial software engineering challenge. Authors are required to specify their challenges with a concise title, provide the context and background of their challenges, identify key technical challenges, and outline the expected technical requirements for solving the corresponding challenges. Submissions must be anonymous. The identity of the challenge proponents will not be revealed after acceptance. Please send your challenge paper by email to the Industry Challenge Track co-chairs, Henry Muccini (henry.muccini@univaq.it) and Filipe Cogo (filipecogo@acm.org).

Submission of Solution Papers

Solution papers must be submitted electronically through the ICSE 2026 Industry Challenge HotCRP submission site: https://icse26-industry-challenge.hotcrp.com/. All submissions must be in English.

Authors are required to specify the title and the abstract of their papers, relevant research areas, the selected challenge, and their conflicts of interest (if any). This information will be used to select qualified reviewers for each submission.

All submissions must be in PDF format and conform, at time of submission, to the official “ACM Primary Article Template”, which can be obtained from the ACM Proceedings Template page. LaTeX users should use the sigconf option, as well as the review (to produce line numbers for easy reference by the reviewers) and anonymous (omitting author names) options. To that end, the following LaTeX code can be placed at the start of the LaTeX document:

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

Submissions must not exceed 10 pages (5 to 10 pages are permitted, one additional page for the camera-ready version) for the main text, including all figures, tables, and appendices. Up to two additional pages containing ONLY references are permitted. All submissions must be anonymous and provide the requirements specified by the relevant challenge. Submissions that do not adhere to these limits or that violate the formatting guidelines will be desk-rejected without review.

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.

IMPORTANT #1: Starting 2026, all articles published by ACM will be made Open Access. This is greatly beneficial to the advancement of computer science and leads to increased usage and citation of research.

• Most authors will be covered by ACM OPEN agreements by that point and will not have to pay Article Processing Charges (APC). Check if your institution participates in ACM OPEN.
• Authors not covered by ACM OPEN agreements may have to pay APC; however, ACM is offering several automated and discretionary APC Waivers and Discounts.

IMPORTANT #2: Submissions must follow the latest “IEEE Submission and Peer Review Policy” and “ACM Policy on Authorship” (with associated FAQ, which includes a policy regarding the use of generative AI tools and technologies, such as ChatGPT.

Conference Attendance Expectation

If a submission is accepted, at least one author of the paper is required to register for ICSE 2026 and present the paper. We are assuming that the conference will be in-person, and if it is virtual or hybrid, virtual presentations may be possible. These matters will be discussed with the authors closer to the date of the conference.

Accepted Challenges

Download all

1. Scalable Automation of ECU Software Artifact Retrieval in Automotive Test Pipelines

   Keywords: Automotive Software, Artifact Management, ECU Test Automation

2. Evaluating Agentic AI Systems: From Performance to Risk

   Keywords: Agents, Risk Assessment, Foundation Models

3. Beyond Syntax: Systematic Evaluation of Structured Text Generation

   Keywords: Structured Text Generation, Semantic Validity, Large Language Models

4. LiveSync Arch: Continuous Synchronization of Architecture Documentation

   Keywords: Automatic Change Detection, Continuous Architecture Synchronization, Living Documentation

5. Proactive Permission Forecasting and Governance for IaC

   Keywords: IaC, Least-Privilege, Zero-Trust, Permission Forecasting

6. AI Assisted Software Domain Modeling For Fast Growing Companies

   Keywords: Domain Modeling, Evolution and Maintenance, Software Design Methodologies

7. BitNet b1.58 - Transforming Industrial Edge Computing

   Keywords: LLM, Quantization, EdgeAI

8. Platform-Independent Automotive Software Components with Model-Driven Engineering

   Keywords: Automotive Software Development Process, Tools and Platform Specifications

9. LLM-Assisted Test Case Generation to Improve Code Coverage in DBMS

   Keywords: DBMS, Large Language Model, Test Generation

10. Assessing the Impact of Generative AI on the Productivity of Software Practitioners

    Keywords: Generative AI, Productivity, Large Language Models

11. GenOps as Code: CI/CD and Infrastructure Patterns for Generative AI Workflows

    Keywords: Automated AI Pipelines, DevOps and GenOps, Machine Learning Operations (MLOps) and Continuous Integration, Delivery of GenAI

12. Towards Unclonable Firmware - Mitigating IoT Reverse Engineering via a Hardware-Anchored Approach

    Keywords: Reverse Engineering, Firmware, IoT, Security

13. Catching License Changes Before They Cost: Leveraging LLMs to Analyze License Evolution in Open Source Software

    Keywords: License Identification, LLMs, Open Source Software

14. Automatically Synthesizing Databases for Critical Performance Bottleneck Reproduction

    Keywords: DBMS, Performance Bugs, Reproducibility

15. Binary Analysis with Machine Learning and Generative AI

    Keywords: Binary Analysis, Generative AI, Machine Learning

16. Real-Time Process Mining from Telemetry Streams: Enabling Causal Diagnoses in Distributed Software Ecosystems

    Keywords: Process Mining, OpenTelemetry, Root Cause Analysis

17. Sound, Precise, and Scalable Call Graph Analysis for C/C++ Programs

    Keywords: Call Graph Analysis, C/C++, Program Analysis

18. Automated Fault Localization in LLM-based Code Agent

    Keywords: Large Language Model, Code Agent, Fault Localization

19. Deceiving the Oracle — A Framework for Adversarial Obfuscation Against LLM-based Code Analysis

    Keywords: Adversarial Obfuscation, Software Security, Reverse Engineering