Bounded Autonomy: Controlling LLM Characters in Live Multiplayer Games
Yunjia Guo, Jinghan Zhu, Siyu Wang, and Haixin Qiao

TL;DR
This paper introduces bounded autonomy, a control architecture for integrating large language model characters into live multiplayer games, ensuring social coherence, controllability, and real-time interaction.
Contribution
It proposes a novel control framework with specific interfaces and techniques, demonstrated through deployment in a live multiplayer social game.
Findings
Bounded autonomy enables stable LLM character interactions in live multiplayer settings.
The architecture allows effective player influence without compromising character autonomy.
Experimental results show improved grounding quality and interaction stability.
Abstract
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.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
