I4Games：一种面向演化博弈的通用策略搜索框架

iscovering strategies with long-term evolutionary advantages in multi-agent systems is a fundamental problem at the intersection of evolutionary game theory, complex systems science, and artificial intelligence. This paper presents a general strategy discovery framework, \textbf{AI4Games}, which systematically transforms strategy design into a reinforcement learningdriven optimization task. The framework abstracts five generalizable componentsstrategy representation, interaction design, reward construction, optimization, and evaluationforming a reusable pipeline applicable to diverse game-theoretic and behavioral modeling settings.To validate the framework, we apply AI4Games to the evolutionary Iterated Prisoners Dilemma and successfully uncover a memory-two bilateral reciprocity strategy (MTBR) that emerges naturally from training. MTBR exhibits interpretable behavioral rules, robust performance across heterogeneous opponents, and strong evolutionary stability. Its emergence as a non-predefined outcome highlights the frameworks capability in navigating high-dimensional strategy spaces and discovering effective behavioral patterns.AI4Games advances strategy modeling beyond hand-crafted heuristics and exemplifies the methodological contribution of AI for Science (AI4S) in the game-theoretic domain. It provides both a theoretical foundation and a practical tool for cross-disciplinary modeling under the AI+ national initiative.