#Game Theory

Articles (13)

• 🇺🇸 Evolutionarily Stable Stackelberg Equilibrium — 20/03/2026 [USA]

  arXiv:2603.18385v1 Announce Type: cross Abstract: We present a new solution concept called evolutionarily stable Stackelberg equilibrium (SESS). We study the Stackelberg evolutionary game setting in ...

  Related: #Evolutionary Stability, #Strategic Leadership
• 🇺🇸 Regret Bounds for Competitive Resource Allocation with Endogenous Costs — 20/03/2026 [USA]

  arXiv:2603.18999v1 Announce Type: new Abstract: We study online resource allocation among N interacting modules over T rounds. Unlike standard online optimization, costs are endogenous: they depend o...

  Related: #Resource Allocation
• 🇺🇸 Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably — 20/03/2026 [USA]

  arXiv:2603.18563v1 Announce Type: new Abstract: AI agents are increasingly deployed in interactive economic environments characterized by repeated AI-AI interactions. Despite AI agents' advanced capa...

  Related: #AI Reasoning
• 🇺🇸 Quantum entanglement provides a competitive advantage in adversarial games — 12/03/2026 [USA]

  arXiv:2603.10289v1 Announce Type: cross Abstract: Whether uniquely quantum resources confer advantages in fully classical, competitive environments remains an open question. Competitive zero-sum rein...

  Related: #Quantum Advantage
• 🇺🇸 Visualizing Coalition Formation: From Hedonic Games to Image Segmentation — 10/03/2026 [USA]

  arXiv:2603.07890v1 Announce Type: new Abstract: We propose image segmentation as a visual diagnostic testbed for coalition formation in hedonic games. Modeling pixels as agents on a graph, we study h...

  Related: #Computer Vision
• 🇺🇸 Maximin Share Guarantees via Limited Cost-Sensitive Sharing — 25/02/2026 [USA]

  arXiv:2602.20541v1 Announce Type: cross Abstract: We study the problem of fairly allocating indivisible goods when limited sharing is allowed, that is, each good may be allocated to up to $k$ agents,...

  Related: #Fair Division, #Resource Allocation, #Multi-agent Systems
• 🇺🇸 A Survey on Hypergame Theory: Modeling Misaligned Perceptions and Nested Beliefs for Multi-agent Systems — 16/02/2026 [USA]

  arXiv:2507.19593v2 Announce Type: replace Abstract: Classical game-theoretic models typically assume rational agents, complete information, and common knowledge of payoffs - assumptions that are ofte...

  Related: #Multi-agent Systems, #Strategic Modeling
• 🇺🇸 GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory — 16/02/2026 [USA]

  arXiv:2602.12316v1 Announce Type: new Abstract: Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evalu...

  Related: #AI Safety, #Multi-agent Systems
• 🇺🇸 Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective — 10/02/2026 [USA]

  arXiv:2602.07259v1 Announce Type: new Abstract: As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversi...

  Related: #Artificial Intelligence, #Cybersecurity
• 🇺🇸 Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia — 09/02/2026 [USA]

  arXiv:2509.23023v2 Announce Type: replace Abstract: Mafia is a social deduction game where informed mafia compete against uninformed townsfolk. Its asymmetry of information and reliance on theory-of-...

  Related: #Artificial Intelligence, #Social Intelligence
• 🇺🇸 LLM Active Alignment: A Nash Equilibrium Perspective — 09/02/2026 [USA]

  arXiv:2602.06836v1 Announce Type: new Abstract: We develop a game-theoretic framework for predicting and steering the behavior of populations of large language models (LLMs) through Nash equilibrium ...

  Related: #Artificial Intelligence, #AI Safety
• 🇺🇸 Communication Enhances LLMs' Stability in Strategic Thinking — 09/02/2026 [USA]

  arXiv:2602.06081v1 Announce Type: cross Abstract: Large Language Models (LLMs) often exhibit pronounced context-dependent variability that undermines predictable multi-agent behavior in tasks requiri...

  Related: #Artificial Intelligence, #Machine Learning
• 🇺🇸 Sample-Efficient Policy Space Response Oracles with Joint Experience Best Response — 09/02/2026 [USA]

  arXiv:2602.06599v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) offers a scalable alternative to exact game-theoretic analysis but suffers from non-stationarity and the ne...

  Related: #Artificial Intelligence, #Machine Learning