VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?

arXiv 2026 24.6 method

TLDR

Proposes VibeWorlding, a benchmark and RL training framework for multimodal agents to construct interactive 3D open worlds from user queries; current MLLMs underperform.

Reasoning

The paper introduces a substantial benchmark and training environment for multimodal 3D world construction, with empirical evaluation of frontier models. However, its core contribution is agent benchmarking and RL post-training rather than world modeling or dynamics prediction, so world-model-related keywords are only weakly relevant.

Read-first score

Read-first score 24.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 11.

Recency 6%

100

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

Methodology quality 18%

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

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Topical relevance 29%

15.7

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

Citation impact 18%

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

Citation velocity 12%

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

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 46.

Keyword Scores

interactive world model

world model

generative world model

world simulator

video world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper