STAF 2025
Tue 10 - Fri 13 June 2025 Koblenz, Germany
Thu 12 Jun 2025 11:00 - 11:30 at D 238 - LLM4SE Session 2

Large Language Models (LLMs) are increasingly utilised in software development, particularly for automatic code generation. Game development, a complex and multidisciplinary field, has begun leveraging LLMs to streamline various stages of the development process. This paper focuses on the application of LLMs in automating code generation for game development, providing a comprehensive survey of existing research from multiple perspectives. We analyse the benefits and limitations of LLM-based approaches in this domain and identify key challenges. Our findings highlight the potential of LLMs to enhance game development workflows, while outlining future research directions to address existing limitations.

Thu 12 Jun

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

11:00 - 12:30
LLM4SE Session 2LLM4SE at D 238
11:00
30m
Research paper
Large Language Models for Game Development: A Survey on Automated Code Generation
LLM4SE
Mohammadreza Sharbaf University of Isfahan, Shekoufeh Rahimi University of Roehampton , Alireza Dastmalchi Saei Bilkent University
11:30
30m
Research paper
A Language Workbench Extension to Generate Conversational Interfaces for Domain-Specific Languages
LLM4SE
Luigi Brandolini IMT Atlantique, LS2N (UMR CNRS 6004), Jean Sebastien Sottet Luxembourg Institute of Science and Technology and University of Luxembourg, Massimo Tisi
12:00
30m
Research paper
AIPyCraft: AI-Assisted Software Development Lifecycle for 6G Blockchain Oracle Validation
LLM4SE
Antonio Alberti University of Leeds, Alexis Leal Federal Institute of Mato Grosso (Brazil), Ariel Dalla-Costa Universidade do Vale do Rio dos Sinos, Cristiano Both University of Vale do Rio dos Sinos (UNISINOS)