19 papers
Divergence-based Safety Measure for Large Language Models via Rational Inattention
Anh Tung Nguyen, Quanyan Zhu
This paper proposes a divergence-based safety measure for large language models (LLMs) under embedding-input attacks. The proposed measure quantifies the worst-case Kullback--Leibl…
Exit-and-Join Dynamics and Equilibrium in Continuum Cooperative Games
Quanyan Zhu
This paper develops a continuum theory of exit-and-join coalition dynamics in nonatomic cooperative games. We extend the Aumann-Shapley value and the Aumann-Drèze value to coaliti…
Multiscale Exit-Join Dynamics: Tactical Consensus and Strategic Coalition Formation
Quanyan Zhu
This paper develops a multiscale model of coalition formation in which strategic exit-and-join decisions are coupled with tactical consensus dynamics inside coalitions. Coalition v…
Exit-and-Join Dynamics for Decentralized Coalition Formation
Quanyan Zhu
This paper studies coalition formation as a decentralized dynamical process driven by unilateral exit-and-join decisions. Agents evaluate local moves using the Aumann-Dreze value,…
A Variational Framework for LLM Generator-Regulator Games
Quanyan Zhu
This paper develops a variational framework for regulated language generation. Starting from autoregressive token sampling, we derive the induced distribution over complete message…
The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale
Quanyan Zhu
The rapid emergence of autonomous AI agents is transforming artificial intelligence from isolated model inference into distributed systems of reasoning, communication, and action.…