GeCoIn

Workshop Program

The workshop will be held on one day in August 15-17, 2026 as part of the IJCAI-ECAI 2026 conference.

The workshop program, including keynote presentations and accepted papers, will be announced after the review process is complete. Stay tuned!

Call for Papers

This workshop aims to offer a shared venue for researchers and practitioners involved in the design, development, and application of generative AI technologies, such as large language models (LLMs), to engage with experts in software engineering, security and verification.

Reasons behind the idea of this workshop arise from the widespread adoption of those cutting-edge AI technologies in the creation of code, which is prevalent in both academic research and industrial settings. As the utilization of these powerful tools continues to grow, there is an increasing necessity to ensure that the code they generate is secure and safe, ideally free from vulnerabilities.

However, controlling AI code generation is challenging because modern, often commercially-used, models operate as black boxes and frequently lack awareness of their own inaccuracies. As a consequence, AI generated code could introduce serious weaknesses in a source code corpora, which could become potentially difficult to identify when the AI tools are used massively. Roads towards a solution to this issue are numerous and open research questions in various fields: static analysis, security, benchmarking, fine-tuning or custom training of AI models, software engineering, explainable AI, and so on.

By bringing together experts from these communities, the workshop aims to foster interdisciplinary collaboration and facilitate the sharing of knowledge, providing a common ground of discussion about possible solutions to this challenge.

Scope

We invite submissions on all aspects related to generative code intelligence, including but not limited to:

• Static and Dynamic Analysis of AI Generated Code
• Safety and Security of AI Generated Code
• Training, Fine-tuning & RAG Techniques for Code Generation and Analysis
• Explainable Methods for AI Code Generation
• LLM Applications in Software Engineering
• Benchmarking of LLMs for Code Tasks

Important Dates

All deadlines are 23:59 AoE (Anywhere on Earth) on the specified date.

Submission Guidelines

We invite submissions in the following two categories:

All submissions must be in English and follow the CEUR single column format. Papers should be submitted only through the workshop's submission system. All submissions will undergo a single-blind peer review process.

Paper will be submitted as PDF documents through EasyChair. The submission link will be announced soon.

The template for the submission can be found at this link https://it.overleaf.com/latex/templates/template-for-submissions-to-ceur-workshop-proceedings-ceur-ws-dot-org/wqyfdgftmcfw.

All submissions will be peer-reviewed by at least three members of the program committee for quality and relevance.

We plan to include all regular papers in the Proceedings of the event, published at CEUR WS proceedings. CEUR WS proceedings are archival proceedings indexed by DBLP and Scopus.

Organization

Eleonora Iotti

University of Parma

Italy

eleonora.iotti@unipr.it

Vincenzo Arceri

University of Parma

Italy

vincenzo.arceri@unipr.it

Greta Dolcetti

Ca' Foscari University of Venice

Italy

greta.dolcetti@unive.it

Sergio Maffeis

Imperial College London

United Kingdom

sergio.maffeis@imperial.ac.uk

Program Committee

Past Editions