Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably

• URL: http://arxiv.org/abs/2603.18563v1
• Date: Thu, 19 Mar 2026 07:24:39 GMT
• Title: Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably
• Abstract summary: We show that off-the-shelf reasoning AI agents can achieve Nash-like play zero-shot without explicit post-training.<n>Our findings suggest that AI agents naturally exhibit such reasoning patterns and therefore attain stable equilibrium behaviors intrinsically.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents are increasingly deployed in interactive economic environments characterized by repeated AI-AI interactions. Despite AI agents' advanced capabilities, empirical studies reveal that such interactions often fail to stably induce a strategic equilibrium, such as a Nash equilibrium. Post-training methods have been proposed to induce a strategic equilibrium; however, it remains impractical to uniformly apply an alignment method across diverse, independently developed AI models in strategic settings. In this paper, we provide theoretical and empirical evidence that off-the-shelf reasoning AI agents can achieve Nash-like play zero-shot, without explicit post-training. Specifically, we prove that `reasonably reasoning' agents, i.e., agents capable of forming beliefs about others' strategies from previous observation and learning to best respond to these beliefs, eventually behave along almost every realized play path in a way that is weakly close to a Nash equilibrium of the continuation game. In addition, we relax the common-knowledge payoff assumption by allowing stage payoffs to be unknown and by having each agent observe only its own privately realized stochastic payoffs, and we show that we can still achieve the same on-path Nash convergence guarantee. We then empirically validate the proposed theories by simulating five game scenarios, ranging from a repeated prisoner's dilemma game to stylized repeated marketing promotion games. Our findings suggest that AI agents naturally exhibit such reasoning patterns and therefore attain stable equilibrium behaviors intrinsically, obviating the need for universal alignment procedures in many real-world strategic interactions.

Related papers

• Playing games with knowledge: AI-Induced delusions need game theoretic interventions [0.34376560669160394]
  We show that sycophantic chatbots induce delusional belief spirals even in rational agents.<n>We propose an inference-time mechanism design intervention called an Epistemic Mediator.
  arXiv  Detail & Related papers  (2026-05-08T19:13:34Z)
• Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning [57.23345786304694]
  We introduce a framework for prospective learning and embedded agency centered on self-prediction.<n>We show that in multi-agent settings, self-prediction enables agents to reason about others running similar algorithms.<n>We extend the theory of AIXI, and study universally intelligent embedded agents which start from a Solomonoff prior.
  arXiv  Detail & Related papers  (2025-11-27T08:46:48Z)
• The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game [0.8594140167290097]
  We analyze the behavior of four reasoning and non-reasoning models across two conditions.<n>We find that, across different settings, telling LLMs that they are playing against themselves significantly changes their tendency to cooperate.<n>While our study is conducted in a toy environment, our results may provide insights into multi-agent settings where agents "unconsciously" discriminating against each other could inexplicably increase or decrease cooperation.
  arXiv  Detail & Related papers  (2025-08-25T20:35:03Z)
• FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory [51.96049148869987]
  We present FAIRGAME, a Framework for AI Agents Bias Recognition using Game Theory.<n>We describe its implementation and usage, and we employ it to uncover biased outcomes in popular games among AI agents.<n>Overall, FAIRGAME allows users to reliably and easily simulate their desired games and scenarios.
  arXiv  Detail & Related papers  (2025-04-19T15:29:04Z)
• Linear Convergence of Independent Natural Policy Gradient in Games with Entropy Regularization [12.612009339150504]
  This work focuses on the entropy-regularized independent natural policy gradient (NPG) algorithm in multi-agent reinforcement learning. We show that, under sufficient entropy regularization, the dynamics of this system converge at a linear rate to the quantal response equilibrium (QRE)
  arXiv  Detail & Related papers  (2024-05-04T22:48:53Z)
• Opponent Modeling in Multiplayer Imperfect-Information Games [1.024113475677323]
  We present an approach for opponent modeling in multiplayer imperfect-information games. We run experiments against a variety of real opponents and exact Nash equilibrium strategies in three-player Kuhn poker. Our algorithm significantly outperforms all of the agents, including the exact Nash equilibrium strategies.
  arXiv  Detail & Related papers  (2022-12-12T16:48:53Z)
• Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks [83.28949556413717]
  We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. We model players' strategies using artificial neural networks. This paper is the first to solve general continuous-action games with unrestricted mixed strategies and without any gradient information.
  arXiv  Detail & Related papers  (2022-11-29T05:16:41Z)
• Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games [51.90475640044073]
  We study adversarial training as an alternating best-response strategy in a 2-player zero-sum game. On the other hand, a unique pure Nash equilibrium of the game exists and is provably robust.
  arXiv  Detail & Related papers  (2022-10-23T03:21:01Z)
• Explore and Control with Adversarial Surprise [78.41972292110967]
  Reinforcement learning (RL) provides a framework for learning goal-directed policies given user-specified rewards. We propose a new unsupervised RL technique based on an adversarial game which pits two policies against each other to compete over the amount of surprise an RL agent experiences. We show that our method leads to the emergence of complex skills by exhibiting clear phase transitions.
  arXiv  Detail & Related papers  (2021-07-12T17:58:40Z)
• Hindsight and Sequential Rationality of Correlated Play [18.176128899338433]
  We look at algorithms that ensure strong performance in hindsight relative to what could have been achieved with modified behavior. We develop and advocate for this hindsight framing of learning in general sequential decision-making settings. We present examples illustrating the distinct strengths and weaknesses of each type of equilibrium in the literature.
  arXiv  Detail & Related papers  (2020-12-10T18:30:21Z)
• On Information Asymmetry in Competitive Multi-Agent Reinforcement Learning: Convergence and Optimality [78.76529463321374]
  We study the system of interacting non-cooperative two Q-learning agents. We show that this information asymmetry can lead to a stable outcome of population learning.
  arXiv  Detail & Related papers  (2020-10-21T11:19:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.