Skip to content
Conference Open access

AI-Assisted Scene Synthesis in the 3D Educational Game Authoring Tool GameTULearn

Sep 2026 · European Conference on Games Based Learning · 0 citations · 22 references

TL;DR

An AI-assisted scene-synthesis workflow that translates prompt-based natural-language descriptions into editable 3D room layouts inside GameTULearn, which supports a hybrid authoring model in which AI accelerates scene creation, but users remain responsible for review and refinement.

Abstract

Educational games can improve motivation and learning outcomes but authoring them is still difficult for educators without programming experience. This problem is particularly visible in 3D scene creation, where users must select assets, arrange objects, and maintain spatial consistency inside a complex editor. GameTULearn addresses this challenge as a no-code authoring environment for interactive 3D educational games. This paper presents an AI-assisted scene-synthesis workflow that translates prompt-based natural-language descriptions into editable 3D room layouts inside GameTULearn. The workflow is designed as an assistive layer rather than an automatic generator. A multi-stage pipeline interprets the user request, selects scene-editing functions, retrieves suitable assets and objects, places them on a structured room grid, and executes the resulting operations in Unity. Low-level implementation details such as object instantiation, placement constraints, and validation remain inside the engine. This separation reduces the decision burden for the language model and keeps the generated scene fully editable. We evaluated the workflow in a within-subject user study with 13 participants. Each participant recreated the same educational game scene once with the AI-assisted workflow and once with a traditional drag-and-drop editor. The AI-assisted workflow reached a System Usability Scale score of 80.6, compared with 69.4 for the traditional condition. Participants particularly valued the lower entry barrier and the reduced interaction effort. At the same time, they criticised mismatches between their descriptions and the generated layouts and did not want to give up manual control. The results therefore support a hybrid authoring model in which AI accelerates scene creation, but users remain responsible for review and refinement.

Read PDF

Similar papers

Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes

This work introduces Code4Scene, a benchmark of 190 Unreal Engine cases built from human-assembled scenes that evaluates coding agents on two complementary settings under a shared execution interface, and exposes a gap between plausible 3D generation and reliable spatial reasoning and state control.

Xiao-Kang Ye, Siddhant Hitesh Mantri, Zi-Meng Chen et al. · 4 citations
Book 2024

Procedural Content Generation with Unreal Engine 5

In the ever-evolving world of games and virtual production, mastering procedural content generator (PCG) opens the door to endless creative possibilities. This book takes you deeper into the realm of procedurally generated environments and assets by showing you how to use the PCG framework integrated into Unreal Engine...

P. Eliasz · 0 citations
Preprint Oct 2026

DyCraft: An Agentic System for Long-Horizon 4D Scene Generation

DyCraft, a system for animated 3D scene generation that breaks animation into steps that coding agents can more reliably solve, substantially reduces physical violations and generates higher-quality animated 3D scenes that are more often preferred by human raters.

Jeff Tan, Hang Dai, Ze-Qian Long et al. · 0 citations
#artificial intelligence Review Oct 2026

UnityBench-Mini3D: Evaluating LLM Agents for 3D Game Development in Unity

Game development stresses coding agents in ways general software engineering does not: correctness depends on how engine APIs, serialized scene state, and runtime behavior interact, not on source code alone. Existing benchmarks mainly target platforms such as Godot and heavily rely on LLM judges or coarse task-level ou...

Yi-Jun Zhou, Ming-Hao Shao, Key Zhang et al. · 1 citation
Book Open access Oct 2026

Multi-Level Modeling for Interactive Scene Description and Content Creation

A multi-level model-based framework: Multi-Layer Content Model (MLCM), that utilizes MLM concepts to describe, store, and transport Digital Content Creation assets, serving as a universal interconnect between DCC tools, game engines, and other DCC-related tools.

Gergely Gembela, Gergely Mezei, F. Somogyi · 0 citations
Review Open access Oct 2026

LLM-Based Waypoint Authoring via Augmented Reality for Human–Robot Interaction

AURaPath is extended, an AR system for interactive 6-DoF waypoint determination on a UR10 collaborative robot using HoloLens2, with a voice modality for hands-free authoring, and the ability to decline out-of-scope input determines whether a model is suitable for the language-mapping tier of the safety-gated architectu...

M. Hashemi, Kasra Mojallal, Saeed Mozaffari et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.