Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models

Source

arXiv

arxiv.org/abs/2607.11594v1

Read the source

Source

Plain-Language Brief

The research paper introduces MAGIC, a system that generates multi-scene game worlds using large language models (LLMs). The system overcomes three obstacles in single-scene methods: cross-scene consistency, in-scene navigability, and the evaluation of transitions. MAGIC uses a four-stage pipeline to turn a natural-language prompt into a runnable game project, enforcing portal reachability and generating scenes with transition scripts. The system outperforms existing single-scene methods on a new benchmark of 100 multi-scene cases.

What the Document Says

  • The paper presents MAGIC, a system that generates multi-scene game worlds using LLMs.
  • MAGIC addresses three obstacles in single-scene methods: cross-scene consistency, in-scene navigability, and transition evaluation.
  • MAGIC is a four-stage pipeline that turns a natural-language prompt into a runnable game project.
  • The system enforces portal reachability using a flood-fill validator.
  • MAGIC generates scenes with transition scripts.
  • The paper introduces a transition-focused evaluation agent for MAGIC.

Key Concepts Mentioned

  • Multi-scene navigation
  • Large language models
  • Game worlds
  • Transition-aware
  • Four-stage pipeline

Claims Made by the Document

  • MAGIC produces an executable project for every case on a new benchmark of 100 multi-scene cases.
  • MAGIC reaches 0.99 precision, 0.95 recall, and 0.96 F1 on end-to-end transition identification.

Evidence Used

  • The text states that MAGIC produces an executable project for every case on a new benchmark of 100 multi-scene cases.
  • The text provides evaluation metrics (precision, recall, F1) for end-to-end transition identification.

Methods / Approach

  • Four-stage pipeline
  • Natural-language prompts
  • Portal reachability enforcement using flood-fill validator

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a defining feature of contemporary 3D games, but authoring it is laborious: every portal must have consistent endpoints on both sides, each interior must remain navigable once it is furnished, and the resulting connectivity must be kept consistent across many files. Recent large language model (LLM) and multimodal LLM (MLLM) scene generators have made single-interior synthesis dramatically cheaper, yet they produce one scene at a time and cannot, by naive repetition, yield a connected multi-scene world. We identify three obstacles that single-scene methods leave unsolved: cross-scene consistency, in-scene navigability, and the evaluation of whether a transition actually works. We present MAGIC, a prompt-to-project system that addresses all three. MAGIC is a four-stage pipeline that turns a single natural-language prompt into a runnable multi-scene game project: it plans a shared transition-aware intermediate representation, specifies each scene while enforcing portal reachability with a flood-fill validator, generates the scenes together with their transition scripts, and combines them into one project. Because existing single-scene fidelity metrics never execute a transition, we further introduce a transition-focused evaluation agent that runs each transition in play. On a new benchmark of 100 multi-scene cases, MAGIC produces an executable project for every case and reaches 0.99 precision, 0.95 recall, and 0.96 F1 on end-to-end transition identification; stage by stage, it recovers more ground-truth portals and yields markedly more navigable layouts than an LLM baseline and Holodeck. Our code is available at https://github.com/sereneee1201/MAGIC/.