20 papers
Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance
Quanyan Zhu
The rapid deployment of agentic AI has introduced complex challenges for the ethics and governance of AI systems. Agents built on large language models act through tools on behalf…
Semantic Cooperative Games for Contribution Attribution in LLM-Based Multi-Agent Systems
Pengyi Jiang, Xiaoguang Zhu, Quanyan Zhu
Contribution attribution has become a central problem in LLM-based multi-agent systems, where final outputs are produced through multiple agents, message exchanges, and ordered wor…
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 coalitio…
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.…
AI Tokenomics: The Economics of Tokens, Computation, and Pricing in Foundation Models
Quanyan Zhu
Tokens have become the practical accounting unit for modern foundation model services, linking information processing, computation, memory use, energy expenditure, pricing, and eco…
Agentomics: Economic Foundations for the Valuation, Attribution, and Pricing of AI Agents in Human-AI Workflows
Quanyan Zhu
Agentic AI systems are increasingly being deployed as productive resources in organizational workflows, yet existing evaluation methods primarily measure isolated technical perform…
RCSP: Risk-Sensitive Conjectural Scenario Planning for Safe Dynamic Robot Navigation
Zhengye Han, Quanyan Zhu
Mobile robots can fail before they collide: a velocity that is safe now may commit the robot to a passage that moving obstacles will soon close. We study this predictive near-miss…
Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs
Ya-Ting Yang, Quanyan Zhu
Modern AI systems increasingly rely on workflows composed of multiple interacting agents, some powered by large language models (LLMs) and others by conventional computational modu…
Performative Scenario Optimization
Quanyan Zhu, Zhengye Han
This paper introduces a performative scenario optimization framework for decision-dependent chance-constrained problems. Unlike classical stochastic optimization, we account for th…
Actionable Recourse in Competitive Environments: A Dynamic Game of Endogenous Selection
Ya-Ting Yang, Quanyan Zhu
Actionable recourse studies whether individuals can modify feasible features to overturn unfavorable outcomes produced by AI-assisted decision-support systems. However, many such s…
Differential Privacy in Generative AI Agents: Analysis and Optimal Tradeoffs
Ya-Ting Yang, Quanyan Zhu
Large language models (LLMs) and AI agents are increasingly integrated into enterprise systems to access internal databases and generate context-aware responses. While such integra…
Learning, Misspecification, and Cognitive Arbitrage in Linear-Quadratic Network Games
Quanyan Zhu, Zhengye Han
We study strategic interaction in linear-quadratic network games where agents act on subjective, misspecified models of their environment. Agents observe noisy aggregate signals ge…
Split-Merge Dynamics for Shapley-Fair Coalition Formation
Quanyan Zhu, Zhengye Han
Coalition formation is often modeled as a static equilibrium problem, neglecting the dynamic processes governing how agents self-organize. This paper proposes a dynamic split-and-m…
A Mathematical Programming Approach to Computing and Learning Berk--Nash Equilibria in Infinite-Horizon MDPs
Quanyan Zhu, Zhengye Han
We study sequential decision-making when the agent's internal model class is misspecified. Within the infinite-horizon Berk-Nash framework, stable behavior arises as a fixed point:…
LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to Spearphishing
Quanyan Zhu
We introduce the framework of LLM-Stackelberg games, a class of sequential decision-making models that integrate large language models (LLMs) into strategic interactions between a…
Reasoning and Behavioral Equilibria in LLM-Nash Games: From Mindsets to Actions
Quanyan Zhu
We introduce the LLM-Nash framework, a game-theoretic model where agents select reasoning prompts to guide decision-making via Large Language Models (LLMs). Unlike classical games…