无需额外训练，AI代理可自发收敛至稳定博弈策略
Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably
- 让AI代理模拟贝叶斯后验采样而非追求期望效用
- 在无限重复博弈中，最终逼近纳什均衡（理论保证）
- 适用于真实市场场景，适合研究AI协作与博弈的学者
随着自主AI代理越来越多地参与在线平台市场，一个根本性问题浮现：这些市场能否产生稳定的战略结果？在重复博弈环境中，纳什均衡是稳定性的重要基准。然而，现有对现成大模型代理的实证研究结果不一，尚不清楚独立部署的代理是否能在无显式战略微调的情况下收敛至均衡行为。本文提供肯定答案：通过扩展理论经济学中的贝叶斯学习文献，我们证明，将AI代理视为贝叶斯后验采样者而非期望效用最大化者时，其在无限重复博弈中必然渐近趋近于弱纳什均衡。进一步分析了阶段收益事前未知、仅能观测私有随机收益的情形，仍获得相同收敛保证。我们在五个重复博弈环境（从囚徒困境到营销促销游戏）中进行实证评估，结果表明，现代AI代理内在的推理与学习特性足以催生AI中介市场的战略稳定性，无需不切实际的全局微调。
原文摘要 · Abstract (English)
As autonomous AI agents increasingly mediate online platform markets, a fundamental question emerges: do these markets generate stable strategic outcomes? In repeated strategic environments, the Nash equilibrium provides a natural benchmark for this stability. However, empirical evidence on off-the-shelf LLM agents is mixed, leaving it unclear whether independently deployed agents can converge to equilibrium behavior without explicit strategic post-training. In this paper, we provide an affirmative answer. Extending the Bayesian learning literature in theoretical economics, we prove that AI agents, acting as Bayesian posterior samplers rather than expected utility maximizers, are guaranteed to eventually become weakly close to a Nash equilibrium in infinitely repeated games. We further extend this analysis to settings in which stage payoffs are unknown ex ante, and agents observe only their privately realized stochastic payoffs, and obtain the same convergence guarantees. Finally, we empirically evaluate these theoretical implications across five repeated-game environments, ranging from the Prisoner's Dilemma to marketing promotion games. Taken together, our findings suggest that strategic stability in AI-mediated markets can emerge from the intrinsic reasoning and learning properties of modern AI agents, without the need for unrealistic universal fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。