发表机构
Carnegie Mellon University（卡内基梅隆大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对大语言模型社会智能体的社会模拟问题，提出混合架构EpisodeSim，结合经典AI结构与LLM，通过实验证明经典AI风格支架可提升社会模拟的连贯性。
AI 中文摘要
大语言模型能够生成在局部层面上合理的社会对话轮次，但流畅的下一轮生成并不足以完成社会模拟。人类的餐厅午餐、酒店入住等互动是具有角色、脚本、物质状态、义务、承诺、时间和结束条件的有限社会场景。我们提出EpisodeSim，一种混合LLM智能体架构，它将经典AI结构表示为通过LLM调用解释的自然语言控制状态。世界主控模块维护共享现实、构建场景、裁决提议的动作、追踪效果与义务，并控制场景结束。在两个保留设置上进行的小型定性消融实验支持这一设计主张：LLM的流畅性提供了局部细节，但连贯的社会模拟受益于随时间组织行为的持久经典AI风格支架。
英文摘要
Large language models can produce locally plausible social turns, but fluent next-turn generation is not enough for social simulation. Human encounters such as restaurant lunches and hotel check-ins are bounded social episodes with roles, scripts, material state, obligations, commitments, timing, and closure conditions. We present EpisodeSim, a hybrid LLM-agent architecture that represents classic-AI structures as natural-language control state interpreted by LLM calls. A World Master maintains shared reality, constructs scenes, adjudicates proposed actions, tracks effects and obligations, and controls closure. Experiments with small qualitative ablations on two held-out settings support a design claim: LLM fluency supplies local texture, but coherent social simulation benefits from persistent classic-AI-style scaffolding that organizes behavior over time.
