ICSE 2026 (series) / LLM4Code 2026 (series) /
LLM4Code 2026 Program
This is the LLM4Code 2026 program - see the full program for ICSE 2026 and all affiliated events.
Filter Program
Dates
Rooms
Tracks
Badges
Your Program
Tue 14 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change
Tue 14 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change
09:00 - 09:10 | OpenningLLM4Code at Oceania I Chair(s): Yiling Lou University of Illinois at Urbana-Champaign, Kexin Pei The University of Chicago, Prem Devanbu University of California at Davis, Lin Tan Purdue University, Lingming Zhang University of Illinois at Urbana-Champaign | ||
09:00 10mDay opening | Openning LLM4Code | ||
09:10 - 10:40 | |||
09:10 30mTalk | Beyond the Scaling Race: The Problems Academia Was Built to Solve LLM4Code Kush Jain Mistral AI | ||
09:40 30mTalk | Hands Off the Terminal: LLM Agents that Build, Test, Analyze, and Reproduce LLM4Code Michael Pradel CISPA Helmholtz Center for Information Security | ||
10:10 30mTalk | Towards Efficient Coding Agents LLM4Code Chao Peng ByteDance | ||
11:00 - 11:35 | Benchmarks and Evaluation of AI Coding AssistantsLLM4Code at Oceania I Chair(s): Yiling Lou University of Illinois at Urbana-Champaign | ||
11:00 10mTalk | SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories LLM4Code Chihao Shen University of Maryland, Connor Dilgren University of Maryland, Purva Chiniya University of Maryland, Luke Griffith University of Maryland, Yu Ding Google DeepMind, Yizheng Chen University of Maryland | ||
11:10 10mTalk | RuberDuckBench: A Benchmark for AI Coding Assistants LLM4Code Ferida Mohammed Bryn Mawr College, Fatma Ayad Bryn Mawr College, Satish Chandra Meta Platforms, Inc., Petros Maniatis Google DeepMind, Elizabeth Dinella Bryn Mawr College | ||
11:20 10mTalk | Benchmarking LLM Commit Message Generation through a Developer-centric Pairwise Preference Framework LLM4Code Lucas Almeida Aguiar State University of Ceará, Matheus Freitas State University of Ceará, Matheus Paixao State University of Ceará, Rafael Carmo Federal University of Ceará | ||
11:30 5mTalk | Evaluating LLMs-Driven Java Code Refactoring from a Developer’s Perspective LLM4Code Javel Freitas Federal University of Ceara, Brazil, Guilherme Vaz Pereira School of Technology, PUCRS, Brazil, Lara Gabrielly Souza Batista Lima University of São Paulo (ICMC/USP), São Carlos - SP, Caio Rian de Sousa Federal University of Ceara, Brazil, Edivar FIlho Federal University of Ceara, Brazil, José Cezar de Souza Filho Université Polytechnique Hauts-de-France, Paulo Maia State University of Ceará, Carla Bezerra Federal University of Ceará (UFC) | ||
11:35 - 12:25 | Developer Experience and Human-AI ProgrammingLLM4Code at Oceania I Chair(s): Yiling Lou University of Illinois at Urbana-Champaign | ||
11:35 10mTalk | Achieving Productivity Gains with AI-based IDE features: A Journey at Google LLM4Code Maxim Tabachnyk Google, Inc., Xu Shu Google, Inc., Alexander Frömmgen Google, Inc., Pavel Sychev Google, Inc., Vahid Meimand Google, Inc., Ilia Krets Google, Inc., Stanislav Pyatykh Google, Inc., Abner Araujo Google, Inc., Kristof Molnar Google, Inc., Satish Chandra Meta Platforms, Inc. | ||
11:45 10mTalk | Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study LLM4Code Michele Merler IBM Research, Rangeet Pan IBM Research, Rahul Krishna IBM Research, Tin Kam Ho IBM Research, Raju Pavuluri IBM T.J. Watson Research Center, Maja Vukovic IBM Research | ||
11:55 10mTalk | Code Roulette: How Prompt Variability Affects LLM Code Generation LLM4Code Andrei Paleyes Department of Computer Science and Technology, Univesity of Cambridge, Diana Robinson University of Cambridge, UK, Radzim Sendyka University of Cambridge, Christian Cabrera University of Cambridge, Neil D. Lawrence Department of Computer Science and Technology, Univesity of Cambridge | ||
12:05 5mTalk | English or Chinese? Investigating the Impact of Prompt Language on Large Language Models for Code Summarization LLM4Code Yijia Tang College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China, Zhiqiu Huang Nanjing University of Aeronautics and Astronautics, Jian Xie Informationization Department (Information Technology Center), Nanjing University of Aeronautics and Astronautics, Nanjing, China, Yaoshen Yu Informationization Department (Information Technology Center), Nanjing University of Aeronautics and Astronautics, Nanjing, China, Bowei Xia College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China, Enya Shen School of Software, Tsinghua University, Beijing, China, Yukun Cao School of Computer Science and Artificial Intelligence, Wuhan Textile University | ||
12:10 10mTalk | The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution LLM4Code Norbert Tihanyi Technology Innovation Institute, Bilel Cherif Technology Innovation Institute, ABU Dhabi, UAE, Mohamed Amine Ferrag United Arab Emirates University, ABU Dhabi, UAE, Richard A. Dubniczky Eötvös Loránd University, Budapest, Hungary, Tamas Bisztray University of Oslo | ||
12:20 10mTalk | An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code LLM4Code | ||
14:00 - 14:50 | Code Generation and OptimizationLLM4Code at Oceania I Chair(s): Lingming Zhang University of Illinois at Urbana-Champaign | ||
14:00 10mTalk | Towards Improving in-IDE Code Completion for Driver Development LLM4Code Batuhan Raif Karagoz Advanced Micro Devices (AMD), Mahesh Jayasankar Advanced Micro Devices (AMD), Saurabh Bodhe Advanced Micro Devices (AMD), Subhayan Roy Advanced Micro Devices (AMD), Lejin Varghese Advanced Micro Devices (AMD), Max Kiehn Advanced Micro Devices (AMD), Yonas Bedasso Advanced Micro Devices | ||
14:10 10mTalk | Multi-task Code LLMs: Data Mix or Model Merge? LLM4Code Mingzhi Zhu Rensselaer Polytechnic Institute, Michele Merler IBM Research, Stacy Patterson Rensselaer Polytechnic Institute, Raju Pavuluri IBM T.J. Watson Research Center, Rahul Krishna IBM Research, Boris Sobolev Cisco | ||
14:20 10mTalk | LLM-Driven SQL Remediation: Towards Safe and Explainable Code for Automated Schema Refactoring LLM4Code Antony Seabra de Medeiros Pontifical Catholic University of Rio de Janeiro, Claudio Cavalcante Pontifical Catholic University of Rio de Janeiro, Nicolaas Ruberg BNDES, Sergio Lifschitz Pontifical Catholic University of Rio de Janeiro Link to publication | ||
14:30 10mTalk | CP-Agent: Agentic Constraint Programming LLM4Code Stefan Szeider Vienna University of Technology (TU Wien) | ||
14:40 10mTalk | Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better? LLM4Code Arastoo Zibaeirad University of North Carolina at Charlotte, Marco Vieira University of North Carolina at Charlotte | ||
14:50 - 15:30 | |||
14:50 10mTalk | Statistical Independence Aware Caching for LLM Workflows LLM4Code Yihan Dai Peking University, Dimitrios Stamatios Bouras Peking University, Haoxiang Jia Peking University, Sergey Mechatev Peking University | ||
15:00 10mTalk | An Empirical Study of C to Rust Translation using Local Large-Language Models LLM4Code Nathan Rutherford Royal Holloway, University of London, Dan O'Keeffe Royal Holloway, University of London | ||
15:10 5mTalk | A Spec-Driven Workflow for AI-Assisted Domain-Driven Development: Insights from Practice LLM4Code Jefferson de Barros Santos FGV EBAPE | ||
15:15 5mTalk | LLM-Powered On-Demand Test Suites in Self-Graded Student Programming Assignments LLM4Code | ||
16:00 - 16:40 | Analysis and Optimization for AI-generated Code (Virtual Session)LLM4Code at Oceania I Chair(s): Kexin Pei The University of Chicago Zoom Link: https://us06web.zoom.us/j/89846180915 | ||
16:00 10mTalk | Do LLMs Dream of Energy-Efficient Code? LLM4Code Antimo Di Bernardo Independent Researcher, Gianluca Capozzi Sapienza University of Rome, Pasquale De Rosa University of Neuchâtel, Daniele Cono D'Elia Sapienza University of Rome, Leonardo Querzoni Sapienza University of Rome, Giuseppe Antonio Di Luna Sapienza University of Rome, Valerio Schiavoni University of Neuchâtel | ||
16:10 10mTalk | A Benchmark for Language Models in Real-World System Building LLM4Code Weilin Jin Peking University, Chenyu Zhao Nankai University, Zeshun Huang Nankai University, Chaoyun Zhang Microsoft, Qingwei Lin Microsoft, Chetan Bansal Microsoft Research, Saravan Rajmohan Microsoft, Shenglin Zhang Nankai University, Yongqian Sun Nankai University, Dan Pei Tsinghua University, Yifan Wu Peking University, Tong Jia Institute for Artificial Intelligence, Peking University, Beijing, China, Ying Li School of Software and Microelectronics, Peking University, Beijing, China, Zhonghai Wu Peking University, Minghua Ma Microsoft | ||
16:20 10mTalk | An Automated Methodology for Generating Labeled Datasets of Semantic Errors in Code LLM4Code Mahmoud Kassem New York University Abu Dhabi, Francisco Ribeiro New York University, Abu Dhabi, Sarah Nadi New York University Abu Dhabi | ||
16:30 10mTalk | Code vs Serialized AST Inputs for LLM-Based Code Summarization: An Empirical Study LLM4Code Shijia Dong School of Computing Science, University of Glasgow, Haoruo Zhao School of Computing Science, University of Glasgow, Paul Harvey University of Glasgow, UK | ||
17:40 - 17:45 | |||
17:40 5mDay closing | Closing and Awards LLM4Code | ||