发表机构
The University of Hong Kong; Peking University; Tsinghua University; Beijing Institute of Mathematical Sciences and Applications (BIMSA)（香港大学; 北京大学; 清华大学; 北京数学科学与应用研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究推出WSE-bench基准，评估开放世界模拟中不同智能体架构的大语言模型故事讲述的持续生成、规范一致性和有意义发展，发现三者存在竞争关系，模型规模仅提升持续生成能力。
AI 中文摘要
大语言模型能够写出流畅的故事，但开放式故事讲述所需的不只是局部流畅度。在演变的世界模拟和人工智能原生游戏中，模型必须在世界变化时保留事实、关系、因果依赖关系和角色状态。我们推出WSE-bench，这是一种过程基准，分别评估动态大语言模型故事讲述中的持续生成、规范一致性和有意义的发展。生成覆盖率记录已执行的计划叙事步骤比例；一致性追踪规范被打破的情况；丰富度衡量分支、玩家塑造的轨迹的发展是否有意义。在前沿模型中，一致性和丰富度未形成平滑的权衡关系：它们的经验帕累托前沿是非凹的，存在多个非支配性中间配置，无法通过任何正线性加权选择。添加结构可丰富轨迹，但不会统一提升一致性，还可能缩短轨迹。模型规模主要提升持续生成能力，在规范一致性或有意义的发展方面未产生可靠增益。这些结果表明，持续生成、规范一致性和有意义的发展是不同且有时相互竞争的能力。WSE-bench通过将叙事评估从成品故事扩展到创造故事的过程，使这些动态变得可见。
英文摘要
Large language models can write fluent stories, but open-ended storytelling requires more than local fluency. In evolving world simulations and AI-native games, models must preserve facts, relationships, causal dependencies, and character states as the world changes. We introduce WSE-bench, a process benchmark that separately evaluates sustained generation, canonical coherence, and meaningful development in dynamic LLM storytelling. Generation Coverage records the proportion of planned narrative steps produced; Consistency tracks when canon breaks; and Richness measures how meaningfully branching, player-shaped trajectories develop. Across frontier models, Consistency and Richness do not form a smooth trade-off: their empirical Pareto frontier is non-concave, with several non-dominated intermediate configurations that no positive linear weighting can select. Added structure can enrich trajectories, but it does not uniformly improve coherence and may shorten them. Model scale chiefly improves sustained generation, without producing reliable gains in canonical coherence or meaningful development. These results show that sustained generation, canonical coherence, and meaningful development are distinct and sometimes competing capacities. WSE-bench makes those dynamics visible by extending narrative evaluation from finished stories to the processes that create them.
