Large language models (LLMs) are bringing richer dialogue and social behavior into games, but they also expose a control problem that existing game interfaces do not directly address: how should LLM characters participate in live multiplayer interaction while remaining executable in the shared game world, socially coherent with other active characters, and steerable by players when needed? We frame this problem as bounded autonomy, a control architecture for live multiplayer games that organizes LLM character control around three interfaces: agent-agent interaction, agent-world action execution, and player-agent steering. We instantiate bounded autonomy with probabilistic reply-chain decay, an embedding-based action grounding pipeline with fallback, and whisper, a lightweight soft-steering technique that lets players influence a character's next move without fully overriding autonomy. We deploy this architecture in a live multiplayer social game and study its behavior through analyses of interaction stability, grounding quality, whisper intervention success, and formative interviews. Our results show how bounded autonomy makes LLM character interaction workable in practice, frames controllability as a distinct runtime control problem for LLM characters in live multiplayer games, and provides a concrete exemplar for future games built around this interaction paradigm.

翻译：大型语言模型（LLM）正在为游戏带来更丰富的对话和社会行为，但也暴露出现有游戏界面尚未直接解决的一个控制问题：LLM角色如何在实时多人交互中既能在共享游戏世界中执行操作、与其他活跃角色保持社会一致性，又能在需要时受到玩家引导？我们将此问题定义为有界自主性，这是一种针对实时多人游戏的控制架构，围绕三个接口组织LLM角色控制：智能体-智能体交互、智能体-世界动作执行以及玩家-智能体引导。我们通过概率性回复链衰减、带有回退机制的基于嵌入的动作接地流水线，以及“低语”——一种轻量级软引导技术（允许玩家在不完全覆盖自主性的情况下影响角色下一步行动）——来实例化有界自主性。我们在一个实时多人社交游戏中部署该架构，并通过交互稳定性分析、接地质量评估、低语干预成功率分析以及形成性访谈研究其行为。我们的结果表明，有界自主性如何使LLM角色交互在实践中可行，将可控性定义为实时多人游戏中LLM角色独特的运行时控制问题，并为未来围绕这一交互范式构建的游戏提供了具体范例。