VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction

arXiv 2026 24.3 method

TLDR

VepAgent uses tool-augmented reinforcement learning and a diagnostic tool library to improve video event prediction by bridging causal transitions.

Reasoning

The paper presents a novel agentic framework for video event prediction, with a curated dataset and composite reward mechanism. However, the abstract is truncated and the evaluation is limited to two benchmarks, with no explicit positioning against world model literature.

Read-first score

Read-first score 24.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 19.

Recency 5%

100

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

Methodology quality 15%

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

Reproducibility 15%

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

Topical relevance 25%

27.1

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%

5.7

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0016

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: 119.

Keyword Scores

world dynamics prediction

video world model

world model

world simulator

interactive world model

generative world model

model-based reinforcement learning world model

Resources

Paper