The 15th International Workshop on Genetic Improvement @ICSE 2026

Christ the Redeemer on Corcovado (Rafael Rabello de Barros, CC BY-SA 3.0, via Wikimedia Commons)

Navigation: Attending, Important Dates, Keynote, Accepted Papers, Schedule, CFP, Workshops Chairs, Program Committee

Attending

The 15th instalment of the GI workshop is expected to take place in Rio de Janeiro, Brazil, co-located with the 48th International Conference on Software Engineering, ICSE 2026, which will be held at the Windsor Barra Hotel.

The Windsor Barra is a beachfront convention hotel with extensive meeting facilities and is part of a larger hospitality complex that includes several other Windsor hotels in the area, offering convenient accommodation options for conference attendees. The hotel is situated directly across from Barra Beach and is a short distance from restaurants, shopping malls such as BarraShopping and VillageMall, and ecological parks.

Barra da Tijuca is easily accessible from Rio de Janeiro’s main airports and is connected to the city center and the South Zone via the BRT (Bus Rapid Transit) and metro system. The venue is approximately 30 minutes by car from key cultural landmarks such as Christ the Redeemer, Sugarloaf Mountain, and the iconic neighborhoods of Copacabana and Ipanema.

The workshop is expected to be held in-person. In case of a virtual or hybrid event, virtual presentations may be possible.

Important Dates

Submission Deadline: 27 October 2025 (Mon) (previously 20 October 2025)
Notification: 24 November 2025 (Mon)
Camera-ready: 26 January 2026 (Mon)
Workshop: 13 April 2026 (Mon) (previously 12 April 2026)

Keynote

We are happy to announce that Dr. Wesley Klewerton Guez Assunção, Associate Professor in the Department of Computer Science, North Carolina State University, USA, will give the keynote speech at GI@ICSE 2026.

Genetic Improvement for Software Modernization, Synergy and Opportunities
TBA

Wesley K. G. Assunção is an Associate Professor with the Department of Computer Science at North Carolina State University. Wesley was a University Assistant in the Institute of Software Systems Engineering (ISSE) at Johannes Kepler University Linz (JKU), Austria (2021-2023); a Postdoctoral Researcher at Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Brazil (2019-2023); and an Associate Professor at Federal University of Technology - Paraná, Brazil (2013 to 2020). He obtained his MSc and PhD in Computer Science from Federal University of Paraná (UFPR) also in Brazil. He published many research papers, in collaboration with students and well-known and international researchers, in conferences like ICSE, ICSME, SANER, MSR, EASE, SPLC, SSBSE, GECCO, to cite some, as well as in journals such as EMSE, IST, and JSS. Wesley has also been serving as reviewers for many conferences and journal, and as organizer of conference, symposiums, workshops, competitions, and meetings.

Accepted Papers

GI-Agent Search-Based LLM Agent for Code Optimization with Genetic Improvement
by Donghyun Lee, William B. Langdon, and Justyna Petke
URL Abstract

GI-Agent integrates Large Language Models (LLMs) into Genetic Improvement (GI) to autonomously optimise computer program source code. GI-Agent uses an LLM to allow multi-generational evolutionary learning. Guided by a memory of past actions, known in AI as reflections, it exploits them to give insight and rationale behind software edits, giving better context-aware, less stochastic, mutations and crossovers. Reflections enable GI-Agent to reason about both earlier compile time and runtime successes and failures, and so refine its strategy over time. Integrated into the Magpie GI framework and evaluated on the SAT4J (Java) and MiniSAT (C++) benchmarks, GI-Agent consistently generates more viable and better variants. By combining few-shot prompting with structured search, GI-Agent demonstrates how LLMs can enhance automated program optimisation.

Improving a Parallel C++ Intel SSE SIMD Linear Genetic Programming Interpreter
by William B. Langdon and Carol Hanna
URL Abstract

We use evolution to speedup the new Single Instruction Multiple Data (SIMD) parallel interpreter for Peter Nordin's linear genetic programming GPengine. MAGPIE (Machine Automated General Performance Improvement via Evolution of software) is provided with existing hand optimised code, its revision history and the Intel 256 bit SSE documentation as XML. Linux mprotect sandboxes whilst performance is given by perf instruction count. In a matter of hours local search automatically sped up 128 lines of manually written parallel C++ SIMD code for the Intel Advanced Vector Extensions (AVX) by 2 %.

Applying Genetic Improvement Techniques for Automated Program Repair of Transpiled Code
by Prasham Jadhwani, Carol Hanna, William B. Langdon, and Justyna Petke
URL Abstract

We use Genetic Improvement (GI)-based Automated Program Repair (APR) techniques for syntax correction on transpiled code produced by both large language models (LLMs) and rule-based translators. LLM-assisted Type Change Operator and Boolean Value Change Operator were added to Magpie, which reduced transpilation bugs from Python to Java by 33% (LLM) and by 18% on rule-based translations.

Databending as a Target for Genetic Improvement
by Erik Fredericks, Byron DeVries, and Reihaneh Hariri
URL Abstract

Genetic improvement (GI) is typically used as an approach for optimizing source code for a particular task, where examples include minimizing runtime, improving energy efficiency, and reducing memory footprint. As with any evolutionary algorithm, GI will optimize for a desired fitness objective and can be coerced into objectives that are not strictly for the improvement of software. This paper presents in-progress work towards using GI as a method for generating glitch art, or artwork that is created by intentionally corrupting files (i.e., databending) to provide an aesthetic or emotional experience. We use the PYGGI framework to explore how code patches can impact an existing glitch art framework, with the goal being to find new and interesting outputs that are different from what can be found with random search.

Schedule

This schedule appears in Rio de Janeiro’s time zone (GMT-3, Brasília Time); compare to your timezone here.
Presentations for full papers are 20 minutes long, followed by 10 minutes for questions.
Presentations for short papers consist of a 10 minute talk, followed by 5 minutes for questions.

The workshop will take place at the Windsor Barra Hotel.
See also the schedule on the ICSE website for easy bookmarking.

Schedule to be announced.

Call For Submissions – Submit Here

We invite submissions that discuss recent developments in all areas of research on, and applications of, Genetic Improvement. The International Workshop on Genetic Improvement is the premier workshop in the field and provides an opportunity for researchers interested in automated program repair and software optimisation to disseminate their work, exchange ideas, and discover new research directions.

Topics of interest include both the theory and practice of Genetic Improvement. Applications of GI include, but are not limited to, using GI to:

Improve runtime efficiency
Decrease memory consumption
Decrease energy consumption
Transplant new functionality
Specialise software
Generate multiple versions of software
Improve low level or binary code
Use of Large Language Models with GI
Use of AI with GI
Repair bugs
GI techniques in industrial settings

The workshop emphasises interaction and discussion between participants.
Authors are encouraged to submit early and in-progress work.

We invite three types of submissions:

Research papers (eight page limit, including references)
Position papers (two page limit, including references)
Extended abstracts (five pages limit, including references, free of APC charges)

Papers should be submitted electronically here and must conform to the ACM conference proceedings template as per the ICSE submission process (template)

Accepted papers must be presented at GI 2026 and will appear in the ICSE workshops volume. The official publication date of the workshop proceedings is the date the proceedings are made available by ACM.

The best paper and best presentation will be awarded during the workshop.

Workshop Chairs

Aymeric Blot is a Senior Lecturer at the University of Rennes and a member of the IRISA research centre in the joint Inria/IRISA DiverSE team. After receiving a doctorate from the University of Lille, focused on automated algorithm design for multi-objective combinatorial optimisation, they moved to University College London to work on software specialization using genetic improvement. Currently working on developing and maintaining the Magpie automated software improvement framework.

Oliver Krauss received his doctorate in 2022 in Pattern Mining and Genetic Improvement in Compilers and Interpeters. His research focuses on mining patterns in software, as well as data, to improve runtime performance and energy consumption. He maintains several open source frameworks, such as Amaru.