paper-with-me

홈 › Papers

Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems

2026-02-16 · Furkan Mumcu, Yasin Yilmaz arxiv

Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally rational decisions can impose negative externalities that degrade system-level performance. We propose Socially-Weighted Alignment (SWA), a game-theoretic framework that modifies inference-time decision making by interpolating between an agent's private objective and an estimate of group welfare via a social weight $λ\in[0,1]$. In a shared-resource congestion game with $n$ agents and congestion severity $β$, we show that SWA induces a critical threshold $λ^*=(n-β)/(n-1)$ above which agents no longer have marginal incentive to increase demand under overload, yielding a phase transition from persistent congestion to stable operation near capacity. We further provide an inference-time algorithmic instantiation of SWA that does not require parameter updates or multi-agent reinforcement learning, and use a multi-agent simulation to empirically validate the predicted threshold behavior.

📄 PDF Abstract BibTeX arXiv:2602.14471

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement LearningDecision Making

Similar Papers 제목 키워드 기반

GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare

2025-10-10 · Siqi Zhu, David Zhang, Pedro Cisneros-Velarde, Jiaxuan You arxiv

Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information seeking, or providing practical guidance. C…

Decision Making

GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory

2026-02-12 · Pepijn Cobben, Xuanqiang Angelo Huang, Thao Amelia Pham, Isabel Dahlgren 외 arxiv

Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evaluate single agents, leaving multi-agent risks such as coordination fai…

LLM Active Alignment: A Nash Equilibrium Perspective

2026-02-06 · Tonghan Wang, Yuqi Pan, Xinyi Yang, Yanchen Jiang 외 arxiv

We develop a game-theoretic framework for predicting and steering the behavior of populations of large language models (LLMs) through Nash equilibrium (NE) analysis. To avoid the intractability of equilibrium computation…

Aligning to Social Norms and Values in Interactive Narratives

2022-05-04 · NAACL 2022 7 · Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi 외

We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games -- environments wherein an agent perceives and interacts with a world through natu…

text-based games

Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching

2025-05-27 · Zhekun Shi, Kaizhao Liu, Qi Long, Weijie J. Su 외

Nash Learning from Human Feedback is a game-theoretic framework for aligning large language models (LLMs) with human preferences by modeling learning as a two-player zero-sum game. However, using raw preference as the pa…

Diversity