arXiv：cs.AI· Changhao Song, Yacong Chen, Hui Gao, Yazhou Zhang, Peng Zhang·· 21 小时前
AffectWorld：评估情绪驱动的未来世界预测基准
AffectWorld: Benchmarking Emotion-Driven Future World Prediction
AI 导读
AffectWorld 是一个评估"情绪-动作-世界状态"链条的世界模型基准，包含 1,498 个日常视频样本及 233 个反事实子集，设置三项任务共八项指标。对 Cosmos3 等五个 SoTA 世界模型的评测显示，世界状态变化得分为 0.100-0.280，反事实情绪敏感度仅 0.027-0.070（[0,1] 区间），暴露出情绪驱动动作后果生成与情绪干预下未来预测的明显差距。
正文
Abstract:The world encompasses both physical environments and human actors. Predicting its evolution requires understanding both physical laws and how emotions shape human actions. However, existing world model benchmarks primarily assess physical plausibility and perceptual quality, leaving emotion-driven world evolution largely this http URL introduce AffectWorld, a benchmark that evaluates the chain Emotion-Action-World State through three tasks: World-State Consistency, Emotion-Action Consistency, and Causal Consistency. It comprises 1,498 everyday video samples annotated with plausible emotions, action tendencies, and atomic world-state constraints. A counterfactual subset of 233 samples tests whether changing an agent's emotion under fixed scene and event conditions yields corresponding changes in actions and consequences. We define eight metrics across the three tasks and an additional counterfactual metric, combining automatic visual assessment with human-calibrated VLM/LLM judgments. Evaluations of five SoTA world models (e.g., Cosmos3) required world-state change scores of 0.100-0.280 and counterfactual emotion sensitivity scores of 0.027-0.070 on a [0, 1] scale. These results reveal substantial gaps in generating the consequences of emotion-driven actions and adapting future predictions to emotional interventions. AffectWorld provides a testbed for advancing world models that capture how emotions shape future physical and social states.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18305 [cs.CV] |
| (or arXiv:2610.18305v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18305 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Changhao Song [view email]
[v1]
Tue, 13 Oct 2026 12:50:40 UTC (4,266 KB)
来源：arXiv：cs.AI · arxiv.org