LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models

TL;DR

This paper introduces LLMER, a framework that uses JSON data generated by large language models to create interactive XR worlds, reducing errors and processing time compared to script-based methods.

Contribution

LLMER is a novel approach that translates natural language into JSON data for XR environments, improving robustness and efficiency over prior script-focused methods.

Findings

Over 80% reduction in token consumption

Around 60% decrease in task completion time

Positive user feedback indicating system effectiveness

Abstract

The integration of Large Language Models (LLMs) like GPT-4 with Extended Reality (XR) technologies offers the potential to build truly immersive XR environments that interact with human users through natural language, e.g., generating and animating 3D scenes from audio inputs. However, the complexity of XR environments makes it difficult to accurately extract relevant contextual data and scene/object parameters from an overwhelming volume of XR artifacts. It leads to not only increased costs with pay-per-use models, but also elevated levels of generation errors. Moreover, existing approaches focusing on coding script generation are often prone to generation errors, resulting in flawed or invalid scripts, application crashes, and ultimately a degraded user experience. To overcome these challenges, we introduce LLMER, a novel framework that creates interactive XR worlds using JSON data generated by LLMs. Unlike prior approaches focusing on coding script generation, LLMER translates natural language inputs into JSON data, significantly reducing the likelihood of application crashes and processing latency. It employs a multi-stage strategy to supply only the essential contextual information adapted to the user's request and features multiple modules designed for various XR tasks. Our preliminary user study reveals the effectiveness of the proposed system, with over 80% reduction in consumed tokens and around 60% reduction in task completion time compared to state-of-the-art approaches. The analysis of users' feedback also illuminates a series of directions for further optimization.