MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis

arXiv 2025 43.1 method, benchmark, system

TLDR

Introduces MoReGen, a physics-grounded text-to-video framework using multi-agent LLMs and simulators, plus MoReSet benchmark to evaluate physical validity via object-trajectory correspondence.

Reasoning

The paper addresses an important gap by benchmarking physical validity in T2V generation and proposing a code-based framework with explicit physics simulation. However, the contributions are more about controlled generation and evaluation than learned world models, and the abstract does not provide evidence of real-world interaction or RL integration.

Read-first score

Read-first score 43.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 15.

Recency 8%

86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%

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

Reproducibility 25%

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

Topical relevance 42%

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

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 596.

Keyword Scores

world simulator

video world model

world dynamics prediction

world model

generative world model

interactive world model

model-based reinforcement learning world model

Resources

Paper