الملخص
Multiplayer world models must ensure that independently controlled views remain consistent with one shared and persistent world. We introduce MultiWorldBench, a diagnostic Minecraft benchmark containing 495 case configurations across seven task suites and ten capabilities, including independent control, cross-view motion, shared-state synchronization, persistence, structural reasoning, concurrent interaction, and delayed revisit. We evaluate Solaris, Gamma-World, and MineWorld, using Engine GT as a reference. Gamma-World achieves the highest ten-capability average among the generated systems at 21.39, followed by Solaris at 20.88 and MineWorld at 1.89, while Engine GT reaches 91.69. Gamma-World performs better on several control, shared-state, and revisit capabilities, whereas Solaris leads in cross-view motion and race-condition consistency. Nevertheless, all generated systems score at most 8.00 on state persistence and 1.33 on structural consistency, and none succeeds in spatial reasoning or building-identity preservation. Human preferences produce the same overall ranking and show strong alignment with the automatic evaluation, with a mean dimension-level Spearman correlation of 0.96. These results show that plausible individual views do not yet constitute a coherent multiplayer world.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Xu, Z., Zhang, R., Hu, R., & Wang, Y. (2026). MultiWorldBench: Do Independently Controlled Views Describe One Shared World? https://omanscience.com/ar/articles/multiworldbench-do-independently-controlled-views-describe-one-shared-world
MLA 9
Xu, Zhangbo, et al. "MultiWorldBench: Do Independently Controlled Views Describe One Shared World?" https://omanscience.com/ar/articles/multiworldbench-do-independently-controlled-views-describe-one-shared-world.
شيكاغو (المؤلف–التاريخ)
Xu, Zhangbo, Ruoxi Zhang, Rui Hu, and Yisong Wang. 2026. "MultiWorldBench: Do Independently Controlled Views Describe One Shared World?" https://omanscience.com/ar/articles/multiworldbench-do-independently-controlled-views-describe-one-shared-world.
هارفارد
Xu, Z., Zhang, R., Hu, R. and Wang, Y. (2026) 'MultiWorldBench: Do Independently Controlled Views Describe One Shared World?', Available at: https://omanscience.com/ar/articles/multiworldbench-do-independently-controlled-views-describe-one-shared-world.
فانكوفر
Xu Z, Zhang R, Hu R, Wang Y. MultiWorldBench: Do Independently Controlled Views Describe One Shared World? https://omanscience.com/ar/articles/multiworldbench-do-independently-controlled-views-describe-one-shared-world
IEEE
Z. Xu, R. Zhang, R. Hu, and Y. Wang, "MultiWorldBench: Do Independently Controlled Views Describe One Shared World?," https://omanscience.com/ar/articles/multiworldbench-do-independently-controlled-views-describe-one-shared-world.