Bounded Autonomy: Controlling LLM Characters in Live Multiplayer Games
This addresses the control problem for game developers integrating LLMs into live multiplayer games, though it is incremental as it builds on existing LLM and game interaction paradigms.
The paper tackled the problem of controlling LLM characters in live multiplayer games to ensure they remain executable, socially coherent, and steerable, by proposing a bounded autonomy architecture with techniques like probabilistic reply-chain decay and whisper steering, and demonstrated its effectiveness in a live game deployment with analyses of interaction stability and grounding quality.
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.