Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs

arXiv 2026 22.2 method, system

TLDR

Introduces Recursive Code World Models, reconstructing complex 3D scenes as executable recursive scene programs from a single image via iterative global-local-global refinement.

Reasoning

The paper proposes a novel recursive representation and construction method for code-based 3D scene reconstruction, with empirical comparisons and ablations supporting its benefits. However, the abstract focuses on static scene reconstruction and does not demonstrate dynamics, interactivity, or broader world-model capabilities.

Read-first score

Read-first score 22.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 15.

Recency 5%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code

Methodology quality 15%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=ablation

Topical relevance 25%

21.4

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Graph prestige 15%

10.9

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0031

Citation impact 15%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 10%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 76.

Keyword Scores

world model

generative world model

world simulator

interactive world model

video world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper