Future of Internetware WorkshopInternetware 2026
Ali Babar
Title: Intent is the New Architecture: Lessons from Engineering Platforms with Spec-Driven AI Collaboration
Abstract: Software engineering is going through a fundamental shift. The bottleneck is no longer writing code by hand. As we enter the AI-native era of software engineering, i.e., AIWare, practitioners are learning that ad hoc prompting and random chat sessions with AI agents fail to scale. AI agents work in the language of implementation, not the language of human intent. Increasingly, developers are expected to work more with their AI coding agents than with their team members. As this paradigm is progressing mostly through trial and error, it is important to share the practices, tools, and processes that work, as well as those that do not.
This talk shares our experiences of adopting spec-driven, architecture-centric development while building engineering platforms for data engineering and digital twins. I will walk through the different stages of our AI-native engineering process and the tools used at each stage, from researching product features and writing the initial specification to generating, testing, and reviewing AI-produced code, while human engineers supervise their respective coding agents. I will also share the practices that enable our AI-native processes to deliver operational AI-powered systems. To demonstrate how our approach works in practice, I will walk through different aspects of an AI-enabled digital-twin engineering platform developed using spec-driven, architecture-centric AI-human collaboration approaches.
Bio: Ali Babar is a Professor in the School of Computer Science and Information Technology at Adelaide University, Australia. Professor Babar is also a Visiting Professor at Ozyegin University, Turkey. He is a co-founder and Chief Inspiration Officer (CIO) of Elevex AI Systems, a startup focused on consulting and engineering for secure and scalable AI-native software. Most recently, he was a theme leader for architecture and platforms for security as a service in the Cyber Security Cooperative Research Centre (CSCRC), a major initiative funded by the Australian government, industry, and research institutions. Within the CSCRC, Professor Babar was the technical lead of one of the largest projects, SOCRATES (Software Security with Focus on Critical Infrastructure), that brought together more than 75 researchers and practitioners from 10 organizations to develop and evaluate novel knowledge- and AI-based platforms, methods, and tools for software security. Recently Prof Babar and his team carry out R&D in the areas of engineering AI-native software systems, AI-ready data, software security and privacy, and human-AI collaboration.
Google Scholar: https://scholar.google.com/citations?user=oagBheUAAAAJ
Zhenchang Xing
Title: AI-Native Requirements Engineering: Vision, Principles, and Early Prototype
Abstract: Large language models (LLMs) promise software from a single sentence, but that fluency solves generation, not the harder problem of knowing what to build and when to trust the result. This talk reframes requirements engineering as a second-order control problem: LLMs supply cognitive “energy,” yet compound uncertainty across humans, AI, tools, and organizations. I will present design principles that make unknowns first-class, as well as the conceptualization of requirements space, cognitive-state maps, fog ledgers, and space-aware AI for requirements engineering. Early prototypes will also be presented, including a Workbench with Space-Aware AI comprising three coordinated personas that drive the exploration, convergence, and validation of requirements. The aim is calibratable trust, not just faster generation.
Bio: Dr. Zhenchang Xing is a Senior Principal Research Scientist and Science Leader of the Software Systems Group at CSIRO. Dr. Xing’s current research focuses on the interdisciplinary areas of software engineering, human-computer interaction, and responsible AI. He has over 200 peer-reviewed publications in prestigious journals and conferences and has received multiple distinguished paper awards from top-tier software engineering conferences, including the ACM SIGSOFT Distinguished Paper Award, IEEE TCSE Distinguished Paper Award, and ACM SIGSOFT Most Influential Paper Award. Dr. Xing was the Program Co-Chair of ICSME 2020 and will serve as the General Co-Chair of APSEC 2027 and Program Co-Chair of FSE 2028.
Ge Li
Title: Software Automation with LLMs — Where Do We Stand?
Abstract: Large language models and agent technologies are advancing rapidly, driving transformative changes in software development tools and paradigms. This report discusses two interrelated issues: the capability boundaries of large language models that support agents and the practical significance of exploring these boundaries; and the potential issues in agent technologies that harness the foundational capabilities of large models, including emerging trends and patterns in this area and their implications for software development. The goal is to stimulate reflection and discussion among the audience.
Bio: Ge Li is a Boya Distinguished Professor at Peking University, a Changjiang Scholar, Vice Director of the Software Engineering Committee of the China Computer Federation (CCF), and Deputy Director of the Beijing Key Laboratory of Cognitive Large Models. He was an early promoter of international research on deep learning-based program understanding and generation. Many of his achievements have been recognized as pioneering works and are widely cited. His research team has consistently maintained a leading position in numerous studies at the intersection of software engineering and artificial intelligence. His research outcomes provide intelligent R&D support for multiple enterprises in the aerospace, finance, and information technology sectors.
Li Li
Title: AI Coding for OpenHarmony
Abstract: This presentation focuses on the practical application of AI coding for OpenHarmony, a newly established mobile platform. It will first introduce the AI-assisted R&D toolchain specifically designed for OpenHarmony. It will then present representative practices from the OpenHarmony ecosystem, particularly the application of AI coding techniques to migrate Android apps to OpenHarmony and the use of AI methods to improve the performance of OpenHarmony apps.
Bio: Li Li is a Professor of Software Engineering at Beihang University, China. His research focuses on mobile software engineering and intelligent software engineering. He has published over 200 papers in high-level journals and conferences, with over 10,000 citations on Google Scholar. He has received 10 Best or Outstanding Paper Awards, including the ICSE 10-Year Most Influential Paper Award. He received the 2024 IEEE TCSE Rising Star Award, the 2023 ACM Beijing Rising Star Award, the 2023 MSR Ric Holt Young Researcher Achievement Award, and the 2020 Australian Research Council Young Researcher Award.
Christoph Treude
Title: Harness Engineering for AI Coding Agents
Abstract: AI coding agents navigate repositories, run commands, and open pull requests with limited human oversight. What they do depends not only on the model but also on the version-controlled files that support every run—context files such as AGENTS.md, skills, subagents, and MCP configurations: the agent’s harness. This talk argues that the harness is a software engineering artifact in its own right, to be tested, linted, and repaired rather than written once and left beside the code. Drawing on seven empirical studies, we show that the harness helps—AGENTS.md can make an agent faster and more token-efficient—but also rots, as configuration files can retain references to code that no longer exists. It is reused without being maintained, as skill adoption is often a one-time copy that is never synchronized with upstream, and it can collide within itself, as similar skill descriptions can make agent routing unstable under controlled conditions. Decades of research on consistency checking, dependency management, and linting transfer directly to this new layer. As practice moves from prompting agents to running autonomous loops around them, keeping the harness correct becomes software engineering’s next maintenance problem.
Bio: Christoph Treude is an Associate Professor of Computer Science in the School of Computing and Information Systems at Singapore Management University. His research aims to improve the quality, reliability, and trustworthiness of software systems, with a current focus on human-AI collaboration in software development and the engineering of the artifacts that steer AI coding agents. His work has received three ACM SIGSOFT Distinguished Paper Awards at ASE 2019, ICSE 2021, and MSR 2025. His research has been funded by Singapore’s Ministry of Education, the Australian Research Council, JSPS, and industry partners including Google, Meta, and IBM. He serves as Associate Editor-in-Chief of IEEE Transactions on Software Engineering and as Program Co-Chair of FSE 2026.
Yulei Sui
Title: Analysis and Testing of AI Models: Challenges and Experiences
Abstract: AI models are increasingly deployed in software systems, raising new challenges for understanding, testing, and improving their reliability. This talk discusses our recent experience in analyzing and testing AI models, with a focus on how ideas from program analysis can support both static and dynamic analysis of neural-network-based systems. Building on our experience with the SVF framework, we are developing ACT, a tool for abstraction-based reasoning and testing of neural network models. The work is motivated by shared foundations between program analysis and neural network verification, including abstraction, constraint reasoning, and symbolic exploration over large input spaces. We discuss practical challenges, early findings, and opportunities for improving the reliability and robustness of AI models.
Bio: Yulei Sui is a Professor at UNSW Sydney. His research focuses on static and dynamic program analysis, with an emphasis on developing open-source frameworks for improving the reliability and quality of software systems. He also studies the intersection of language models and software engineering. His work has appeared in conferences and journals in program analysis and software engineering and has received recognition through distinguished paper awards at ICSE, FSE, OOPSLA, and SAS. His research has been supported by the Australian Research Council, JSPS, and industry funding from Google and Amazon.
Dan Dongseong Kim
Title: Cyber G.A.M.E.: Security Research for Trustworthy Connected Systems in the Internetware Era
Abstract: This talk presents Cyber G.A.M.E., a research framework for trustworthy connected systems in the Internetware era. The framework covers Graphical Security Models, AI for Cybersecurity and Security for AI, Moving Target Defence, and Evolving Attacks and Defence Automation. Drawing on selected work in the Internet of Things, autonomous vehicles, intrusion detection, adversarial AI, and cyber-physical systems, the talk will discuss key security challenges and research directions for building secure, resilient, and trustworthy Internetware.
Bio: Dan Dongseong Kim is an Associate Professor in Cyber Security at the School of Electrical Engineering and Computer Science, The University of Queensland, Australia, and Deputy Director of UQ Cyber Security. He leads the Dependable and Secure Systems Lab. His research interests include cybersecurity, dependable systems, graphical security modelling, moving target defence, adversarial machine learning, network security, and the security of cyber-physical and autonomous systems. He has served as General Chair of IEEE/ACM IWQoS 2025, IEEE/IFIP DSN 2024, ACISP 2019, and IEEE PRDC 2017, and is currently Steering Committee Chair of IEEE PRDC. He also served as a Steering Committee member of IEEE/IFIP DSN from 2021 to 2025. He is an Associate Editor of IEEE Communications Surveys & Tutorials and serves on the editorial boards of Elsevier Computers & Security and Elsevier Computer Networks. He is also an elected member of IFIP Working Group 10.4 on Dependable Computing and Fault Tolerance, a selective international working group of approximately 60 members worldwide.
Patanamon Thongtanunam
Title: Unlocking the Potential of LLMs with Care: Can They Really Understand Code Changes?
Abstract: Large language models (LLMs) have shown a remarkable ability to generate text across various domains, including code. However, there is growing concern about hallucinations and whether LLMs can truly understand tasks and the internal representations of code. In this talk, I will review LLMs’ abilities in code-related tasks through the lens of transferable knowledge. In particular, I will argue that although these models can perform well on benchmarks involving restricted contexts and tasks, they lack a fundamental understanding of software beyond the contexts they have seen. I will also present our empirical findings and measurements that highlight the shortcomings of LLMs in tasks where context and prior knowledge are essential, along with our research agenda and directions for unlocking their full potential in developer-facing tasks.
Bio: Dr. Patanamon Thongtanunam, also known as Pick, is an Associate Professor in the School of Computing and Information Systems at the University of Melbourne. Her research interests include empirical software engineering, data mining, and data-driven techniques to support software engineering tasks. Her research work and endeavors have received numerous prestigious awards, including an Australian Research Council Discovery Early Career Researcher Award from 2021 to 2024, the ACM SIGSOFT Distinguished Paper Award, the IEEE Computer Society TCSE Distinguished Paper Award, and distinguished reviewer awards.
Sat 18 JulDisplayed time zone: Brisbane change
08:00 - 17:00 | RegistrationResearch Track | ||
08:45 - 09:00 | OpeningResearch Track | ||
11:40 - 12:40 | Session 1: Software Vulnerabilities and Security IResearch Track at Ballroom Chair(s): Yi Song School of Computer Science, Wuhan University | ||
11:40 15mTalk | LiveFuzz: Detecting Exploitable Library Vulnerabilities from Client Programs via Directed Greybox Fuzzing Research Track Yukai Zhao , Menghan Wu Zhejiang University, Xing Hu Zhejiang University, Shaohua Wang Central University of Finance and Economics, Meng Luo The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Xin Xia Zhejiang University | ||
11:55 15mTalk | ATTAIN: Automated Exploit Failure Analysis through Trace-Driven Diff Analysis Research Track Xinwei Mao Zhejiang University, Zirui Chen Zhejiang University, Xing Hu Zhejiang University, Xin Xia Zhejiang University Pre-print | ||
12:10 15mTalk | VulnForge: Building Enhanced OSS Vulnerability Datasets via Uncertainty-based Patch Analysis Research Track Li Lu Huazhong University of Science and Technology, Xinyu She Huazhong University of Science and Technology, Shengming Zhao Fudan University, Ningke Li National University of Singapore, Yanjie Zhao Huazhong University of Science and Technology, Haoyu Wang Huazhong University of Science and Technology | ||
12:25 15mTalk | RelocSC: Compiler-Driven Generation of Self-Relocating Linux Shellcode Research Track Ruimin Wang Information Engineering University, Jintao Bao Information Engineering University, Jian Lin Information Engineering University, Guoan Liu Information Engineering University, Shuai Ren Information Engineering University | ||
11:40 - 12:35 | Session 2: Code Search and GenerationResearch Track / Tool Demonstration at Promenade Chair(s): Jia Li Wuhan University | ||
11:40 15mTalk | RefAgent: Discovering High-Usability References for Context-Aware Code Generation Research Track Haizhuo Yuan Peking University, Siqiao Yan Peking University, Yanzhen Zou Peking University, Tongwei Deng Peking University, Junfeng Wang Peking University, Yujie Shi Peking University, Xutian Li Peking University, Bing Xie Peking University | ||
11:55 15mTalk | IVGen: Multi-Agent Code Generation via Interleaved Verification for Closed-Loop Robotic Manipulation Research Track Chenghao Fan Zhejiang Sci-Tech University, Yangyang Zhao Zhejiang Sci-Tech University, Ke Ding Hinyeung Technology Co., Ltd, Liming Nie | ||
12:10 15mTalk | SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training Research Track Keyu Liang Zhejiang University, Haoye Wang Hangzhou City University, Yanfu Yan Zhejiang University, Zhiyuan Wan Zhejiang University, Zhongxin Liu Zhejiang University | ||
12:25 10mTalk | Seeing the Forest for the Trees: Repository-Level Version Change Summarization Tool Demonstration Junlin Zhou the School of Software Engineering, Xi’an Jiaotong University, Xi’an, China, Wuxia Jin Xi'an Jiaotong University, Zijun Wang the School of Software Engineering, Xi’an Jiaotong University, Xi’an, China, Jiale Li the School of Software Engineering, Xi’an Jiaotong University, Xi’an, China, Ting Liu Xi'an Jiaotong University | ||
14:00 - 15:30 | Session 3: Software Vulnerabilities and Security IIResearch Track / New Idea at Ballroom Chair(s): Ruitao Feng Southern Cross University | ||
14:00 15mTalk | CaVulner: Automated Context-Aware Identification of Vulnerable Versions Research Track Xiaoyong Yan Zhejiang University, Chengwei Liu Nankai University, Yukai Cao Zhejiang University, Zhiyao Wu Zhejiang University, Rui Chang Zhejiang University, Wenbo Shen Zhejiang University | ||
14:15 15mTalk | Unveiling Large Language Model Supply Chain: Structure, Domain, and Vulnerabilities Research Track Yanzhe Hu Huazhong University of Science and Technology, Shenao Wang Huazhong University of Science and Technology, Yuhan Tang Huazhong University of Science and Technology, Tianyuan Nie Huazhong University of Science and Technology, Yanjie Zhao Huazhong University of Science and Technology, Haoyu Wang Huazhong University of Science and Technology Pre-print | ||
14:30 15mTalk | Demystifying LLM Supply Chain Vulnerabilities in the Wild: Distribution, Root Cause, and Real-World Impact Research Track Shenao Wang Huazhong University of Science and Technology, Yanjie Zhao Huazhong University of Science and Technology, Zhao Liu 360 AI Security Lab, Quanchen Zou 360 AI Security Lab, Haoyu Wang Huazhong University of Science and Technology Pre-print | ||
14:45 15mTalk | Exploring Large Language Models for Security Bug Localization: An Empirical Study Research Track Jiachen Ge State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China, Feifei Niu Graz University of Technology, Chuanyi Li Nanjing University, Xin Xia Zhejiang University | ||
15:00 15mTalk | DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection Research Track Mingyang Sun Institute of Information Engineering, Chinese Academy of Sciences, Guozhu Meng Institute of Information Engineering, Chinese Academy of Sciences Pre-print | ||
15:15 15mTalk | LiveSafeRust: Toward Live Static Security Analysis in the Rust LSP Edit Loop New Idea | ||
14:00 - 15:30 | Session 4: Software TestingResearch Track at Promenade Chair(s): Xinguo Feng The University of Queensland | ||
14:00 15mTalk | DFuzz: Differential Fuzzing for Silent Errors in LLM Operator Optimizations Research Track Jiayi Wang Nanjing University, Zihan Tang Nanjing University, Daohan Qu Nanjing University, Zenan Li ETH Zurich, Yuan Yao Nanjing University, Taolue Chen Birkbeck, University of London, Xiaoxing Ma Nanjing University | ||
14:15 15mTalk | Understanding Bugs in Vector Database Management Systems Research Track Yinglin Xie Huazhong University of Science and Technology, Xinyi Hou Huazhong University of Science and Technology, Yanjie Zhao Huazhong University of Science and Technology, Shenao Wang Huazhong University of Science and Technology, Kai Chen Huazhong University of Science and Technology, Haoyu Wang Huazhong University of Science and Technology | ||
14:30 15mTalk | Segmented Search for Maximum Error Detection in Floating-Point Arithmetic Expressions Research Track dmy Information Engineering University, Fei Li Information Engineering University, Jinchen Xu Information Engineering University, Hongru Yang Hunan University, Changsha, China, Tao Zhang Information Engineering University, Jiaxin Feng Information Engineering University, Bei Zhou Information Engineering University | ||
14:45 15mTalk | GapFuzz: Cross-Plane Divergence Fuzzing for Distributed SDN Controllers Research Track Moustapha Awwalou DIOUF SnT, University of Luxembourg, Samuel Ouya Cheikh Hamidou KANE Digital University, Jacques Klein University of Luxembourg, Tegawendé F. Bissyandé University of Luxembourg Pre-print | ||
15:00 15mTalk | HardRace: A Data Race Monitor for Production Use Research Track Xudong Sun , Zhuo Chen , Jingyang Shi Nanjing University, Yiyu Zhang Nanjing University, Peng Di Kunlunxin & UNSW Sydney, Fengwei Zhang Southern University of Science and Technology, Jianhua Zhao Nanjing University, China, Zhiqiang Zuo Nanjing University | ||
15:15 15mTalk | Generative Reasoning vs. Conventional Analysis: How Well Do LLMs Detect Data Races in Concurrent Programs? Research Track Xinyin Liao Xidian University, Zhiwei Lin Xidian University, Cheng Wen Xidian University, Jie Su Xidian University, Shengchao Qin Xidian University, Xiaoxue Ma City University of Hong Kong, Xiaofeng Li Beijing Institute of Control Engineering, Cong Tian Xidian University Media Attached | ||
15:30 - 16:00 | Coffee BreakCatering | ||
16:00 - 17:30 | Session 5: Program Analysis, Verification, and Code TransformationResearch Track / New Idea at Ballroom Chair(s): Zihan Wang The University of Queensland and CSIRO's Data61 | ||
16:00 15mTalk | Bypassing Redundant Safety Checks in Rust via Static Analysis Research Track Yunlong Yu Shandong University, Qingdan Meng Shandong University, Wei Zhang Shandong University, Lei Ju Shandong University | ||
16:15 15mTalk | Feedback-Oriented Retrieval and Guided Editing for Java Meta-Decompilation Research Track | ||
16:30 15mTalk | Value Analysis of Floating-Point Fortran Programs by Combining Interval and Zonotopic Abstractions Research Track Dengping Wei National University of Defense Technology, Banghu Yin College of Computer, National University of Defense Technology, Changsha, China, Yi Huang National University of Defense Technology, Liqian Chen National University of Defense Technology File Attached | ||
16:45 15mTalk | Editor Specialization: Deriving DSL Editors through Editing Service Lifting Research Track Ziheng Wang Peking University, Zhichao Guan Peking University, Xiaoyang Lu Purdue University, Di Wang Peking University, Hongjie Chen Peking University, Zhenjiang Hu Peking University File Attached | ||
17:00 15mTalk | Predicates with One Hole for Linked Data Structures in Separation Logic Research Track Xingpeng Liu National University of Defense Technology, Yanjun Wen National University of Defense Technology, Hengzhu Liu National University of Defense Technology, Ji Wang National University of Defense Technology | ||
17:15 15mTalk | ACSLAgent: Generation and Synthesis of Formal Specifications for C programs via LLM-based Agent New Idea Lezhi Ma Nanjing University, Han Wang Nanjing University, Shangqing Liu Nanjing University, Lei Bu Nanjing University | ||
16:00 - 17:30 | Session 6: Software Architecture, Systems, and ToolingResearch Track / Tool Demonstration at Promenade Chair(s): Yuekang Li UNSW | ||
16:00 15mTalk | Aurora: A Low-Overhead API Gateway for Authentication-Intensive Mobile Backend-for-Frontend Traffic Research Track Huanran Zuo East China Normal University, Chengcheng Wan East China Normal University, Meng Shi IM Motors, Yiwen Ji IM Motors | ||
16:15 15mTalk | Mosaic: Enabling Inter-Node Memory Sharing for Microkernel-Based Edge Devices Research Track Tianyao Gong Shanghai Jiao Tong University, China, Shengan Zheng Shanghai Jiao Tong University, Zhenlin Qi Shanghai Jiao Tong University, Yingqi Jie Shanghai Jiao Tong University, Yuting Feng Shanghai Jiao Tong University, Linpeng Huang Shanghai Jiao Tong University | ||
16:30 15mTalk | ARTIVM: Adaptive Real-Time Inter-VM Communication Framework for Mixed-Criticality Flows in Multi-core Ubiquitous Operating System Research Track Zixu Bao Northwestern Polytechnical University, Yu Zhang , Huan Guo Northwestern Polytechnical University, Xianglin Lin Northwestern Polytechnical University, Ming Shen Northwestern Polytechnical University | ||
16:45 15mTalk | TRM-Raft: A Byzantine-Resistant Raft Consensus via Integrated Trust and Reputation Model Research Track jie zhang School of Cybersecurity, Tianjin University, Xubo Fan Tianjin University, Xiaohong Li Tianjin University, Zhiyong Feng Tianjin University Pre-print Media Attached | ||
17:00 10mTalk | Hyper-TS: Generative Diffusion Tool for Time Series Data in Cloud Workload Simulation Tool Demonstration File Attached | ||
17:10 10mTalk | VisScaler: Visualization-Augmented Microservice Autoscaling Tool Tool Demonstration Tao Huang , Shengyuan Guan Harbin Institute of Technology, Shenzhen, Cuiyun Gao Harbin Institute of Technology, Shenzhen, XInyue Hu Harbin Institute of Technology, Shenzhen, Guodong Fan Shandong Agriculture and Engineering University, Xin-Cheng Wen Harbin Institute of Technology, Qing Liao Harbin Institute of Technology File Attached | ||
17:20 10mTalk | GramVarKit: A Rule-Driven Toolkit Generator for Exploring AI-Oriented Grammar Variants Tool Demonstration Cenyuan Zhang Monash University, Zhensu Sun Singapore Management University, Dangfeng Pan , David Lo Singapore Management University, Xiaoning Du Monash University File Attached | ||
18:00 - 20:00 | |||
Sun 19 JulDisplayed time zone: Brisbane change
08:00 - 17:00 | RegistrationResearch Track | ||
09:45 - 10:00 | Group PhotoCatering | ||
10:00 - 10:30 | Coffee BreakCatering | ||
11:40 - 12:40 | Session 8: Software Maintenance, Repair, and DevOpsResearch Track / New Idea at Promenade Chair(s): Kaifeng Huang Tongji University | ||
11:40 15mTalk | Fixing Atomicity Violations via Task-driven Dynamic Code Abstraction and Repair Research Track | ||
11:55 15mTalk | LLMs as Continuous Learners: Improving Software Issue Reproduction by Distilling Experiences Research Track Yalan Lin Shanghai Jiao Tong University, Silin Chen Shanghai Jiao Tong University, Yingwei Ma Tongyi Lab, Alibaba, Rongyu Cao Tongyi Lab, Alibaba, China, Binhua Li Tongyi Lab, Alibaba, China, Fei Huang Tongyi Lab, Alibaba, China, Xiaodong Gu Shanghai Jiao Tong University, Yongbin Li Tongyi Lab, Alibaba, China | ||
12:10 10mTalk | When Should Dependency Updates Invoke Repair Agents? A Lightweight Routing Study New Idea Liheng Fan China Academy of Telecommunication Technology, Jialun Yin School of Vehicle and Mobility, Tsinghua University, Yuzhi Chen Intelligent Transportation System Research Center, Southeast University | ||
12:20 10mTalk | WERCA: Workflow-guided and Evidence-constrained Root Cause Analysis for DevOps Systems New Idea yi zhang , Yonghang Wu Beijing XingYun Digital Technology Co., Ltd, Xin Ma Beijing XingYun Digital Technology Co., Ltd, Xinhang Yin Beijing XingYun Digital Technology Co., Ltd, Bing Han Beijing XingYun Digital Technology Co., Ltd, Yijian Zheng Xidian University, Chenxi Zhang Xidian University, Di Cui Xidian University | ||
12:30 10mTalk | Rethinking Agent Memory for Routine Code Fixes: MarkovFix Beats Frontier Agents on Deployable LLM New Idea Zhiqing Zhong The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Jonathan Kristian Tjandra The Chinese University of Hong Kong, Shenzhen, Feivel Ehren Hermanto The Chinese University of Hong Kong, Shenzhen, Ruizhe Ye Huawei Cloud Computing Technologies Co., Ltd., Jingyuan Tan Huawei Cloud Computing Technologies Co., Ltd., Yuechan Hao Huawei Cloud Computing Technologies Co., Ltd., Yuchi Ma Huawei Cloud Computing Technologies, Pinjia He Chinese University of Hong Kong, Shenzhen | ||
14:00 - 15:00 | Session 9: OpenHarmony, IoT, and Edge SecurityResearch Track at Ballroom Chair(s): Jinyu Gu Shanghai Jiao Tong University | ||
14:00 15mTalk | HapCiD: Detecting API-related Compatibility Issues in OpenHarmony Apps Research Track Daihang Chen Beihang University, Yonghui Liu Australian National University, Mingyi Zhou Beihang University, Li Li Beihang University | ||
14:15 15mTalk | Arktan: A Taint Analysis Framework for HarmonyOS ArkTS Application Research Track Ning Zhang Xidian University, Xiaofeng Zhu Xidian University, Haotian Wu Xidian University, Junhao Zhang Xidian University | ||
14:30 15mTalk | XTaint: Dynamic-Assisted Taint Tracking across Execution Boundaries in IoT Firmware Research Track Zuozheng Zhou Information Engineering University, Ruimin Wang Information Engineering University, Jian Lin Information Engineering University, Haoran Liu Information Engineering University, Weiyu Dong Information Engineering University | ||
14:45 15mTalk | Securing the OpenHarmony Software Supply Chain: LLM-Based Malicious Code Detection for ArkTS Research Track Xuetao Li Beijing Institute of Technology, Shencheng Dou China Software Testing Center, Xin Tan Shanghai Huawei Technologies Co., Ltd, Bohan Wang , Jinyuan Wang Beijing Institute of Technology, Yuxia Zhang Beijing Institute of Technology, Guangtai Liang Huawei Cloud Computing Technologies, Hui Liu Beijing Institute of Technology | ||
14:00 - 15:00 | Session 10: Empirical Software EngineeringResearch Track at Promenade Chair(s): Moustapha Awwalou DIOUF SnT, University of Luxembourg | ||
14:00 15mTalk | What Static Features Reveal About Ransomware: An Empirical Study Research Track | ||
14:15 15mTalk | When LLMs Invent Rust Crates: An Empirical Study of Hallucination Patterns and Mitigation Research Track Jieming Zheng Southern University of Science and Technology, Hao Guan Nankai University, Yepang Liu Southern University of Science and Technology Pre-print | ||
14:30 15mTalk | Studying the Effectiveness of Social Media on Open Source Donation Platforms: An Empirical Study Research Track Shuoxiao Zhang State Key Laboratory for Novel Software Technology Nanjing University, Nanjing, China, Enyi Tang Nanjing University, Xinyu Gao Nanjing University, Haoliang Cheng Nanjing University, An Guo The Hong Kong Polytechnic Universituy, Xu Zhou Nanjing University, Lingyun Situ Nanjing University, Xin Chen Nanjing University, Jianhua Zhao Nanjing University, China, Linzhang Wang Nanjing University, Xuandong Li Nanjing University | ||
14:45 15mTalk | Can LLMs Capture Developers' Practical Needs for Code Summarization? An Empirical Study of Code Summary Optimization Behaviors on GitHub Research Track xianwei wu Nanjing University, Haifeng Shen Southern Cross University, Guoping Rong Nanjing University File Attached | ||
15:00 - 15:30 | Coffee BreakCatering | ||
15:30 - 16:40 | Session 11: Software Analytics and Code ReviewResearch Track at Ballroom Chair(s): Yun Peng The Chinese University of Hong Kong | ||
15:30 17mTalk | KA-DA: Aligning LLMs with Expert Knowledge for Fine-Grained Software Defect Analysis Research Track Xuwen Wang National University of Defense Technology China, Jiaxin Li National University of Defense Technology China, Ruibo Wang National University of Defense Technology, Lin Peng National University of Defense Technology China, Linjin Wei National University of Defense Technology China, Zhen Zhu National University of Defense Technology China, Haodi Lu National University of Defense Technology China | ||
15:47 17mTalk | AgentGraph: Knowledge-Graph Augmented Agent Framework for Multi-Step Association Analysis Research Track houyuxuan East China Normal University, Junyuan Guo East China Normal University, Qiyuan Wang East China Normal University, Dongyi Ouyang East China Normal University, Junjie YAO | ||
16:05 17mTalk | MERC-Annot: Automated Annotation of Modification-Eliciting Code Review Comments with Large Language Models Research Track YongdaYu Nanjing University, Lei Zhang Nanjing University, Guoping Rong Nanjing University, Haifeng Shen Southern Cross University, Jiahao Zhang Nanjing University, Haoxiang Yan Nanjing University, Guohao Shi Nanjing University, Dong Shao Nanjing University, He Zhang Nanjing University File Attached | ||
16:22 17mTalk | Don’t Rush to Critique: Cultivating an Analysis-First Habit in Code Review Models Research Track YongdaYu Nanjing University, Guohao Shi Nanjing University, Long Xianjun China Telecom Research Institute, Guoping Rong Nanjing University, Haifeng Shen Southern Cross University, XueMing Gu University of Waterloo File Attached | ||
15:30 - 16:40 | Session 12: Emerging Software Applications and ToolsResearch Track / New Idea / Tool Demonstration at Promenade Chair(s): Yonghui Liu Australian National University | ||
15:30 14mTalk | GPG: A Pragmatics-Aware Graph Framework for Situational Retrieval in Green Technology Transfer Research Track Zhang Shuhui , Ziyun Zhang Peking University, Yuzhe Zhang Beijing University of Technology, Huaqian Cai Peking University, Zhiqiang Li Beijing Institute of Technology, Chunfu Zhang China BeiJing Green Exchange File Attached | ||
15:44 14mTalk | UMS: A Plug-and-Play Model Shielding System for Secure On-Device LLM Deployment Research Track Zihan Zhao Shanghai Jiao Tong University, Jinyu Gu Shanghai Jiao Tong University, Yubin Xia Shanghai Jiao Tong University, China, Haibo Chen Shanghai Jiao Tong University | ||
15:58 14mTalk | PageWeave: Generating Multi-Page HarmonyOS App Prototypes from Screenshots Tool Demonstration Yayun Jiang Nanjing University, Yuanheng Li Nanjing University, Dongshen Rao Nanjing University, Chuanyi Li Nanjing University | ||
16:12 14mTalk | RoboStudio: A Containerized Unified Platform for Embodied-AI Algorithm Integration, Visualization, and Comparison Tool Demonstration | ||
16:26 14mTalk | Space-Native Software New Idea Jinfeng Wen Beijing University of Posts and Telecommunications, Shangguang Wang Beijing University of Posts and Telecommunications | ||
Mon 20 JulDisplayed time zone: Brisbane change
08:00 - 12:30 | RegistrationResearch Track | ||
08:45 - 10:15 | |||
08:45 45mTalk | Invited Talk 1: Intent is the New Architecture: Lessons from Engineering Platforms with Spec-Driven AI Collaboration Future of Internetware Workshop Muhammad Ali Babar The University of Adelaide | ||
09:30 45mTalk | Invited Talk 2: AI-Native Requirements Engineering: Vision, Principles, and Early Prototype Future of Internetware Workshop Zhenchang Xing CSIRO's Data61 | ||
10:15 - 10:35 | Coffee BreakCatering | ||
10:35 - 12:05 | |||
10:35 45mTalk | Invited Talk 3: Software Automation with LLM —— Where Do We Stand？ Future of Internetware Workshop Ge Li Peking University | ||
11:20 45mTalk | Invited Talk 4: AI Coding for OpenHarmony Future of Internetware Workshop Li Li Beihang University | ||
13:05 - 14:35 | |||
13:05 45mTalk | Invited Talk 5: Harness Engineering for AI Coding Agents Future of Internetware Workshop Christoph Treude Singapore Management University | ||
13:50 45mTalk | Invited Talk 6: Analysis and Testing of AI Models: Challenges and Experiences Future of Internetware Workshop Yulei Sui University of New South Wales | ||
14:35 - 14:55 | Coffee BreakCatering | ||
14:55 - 16:25 | |||
14:55 45mTalk | Invited Talk 7: Cyber G.A.M.E.: Security Research for Trustworthy Connected Systems in the Internetware Era Future of Internetware Workshop Dan Dongseong Kim The University of Queensland | ||
15:40 45mTalk | Invited Talk 8: Unlocking the Potential of LLMs with Care: Can They Really Understand Code Changes? Future of Internetware Workshop Patanamon Thongtanunam The University of Melbourne | ||
16:25 - 16:40 | ClosingResearch Track | ||