This paper addresses the optimization challenges in Vehicle-to-Grid (V2G) systems and explores the application of artificial intelligence (AI) methods to solve these challenges. V2G systems enable bidirectional energy flow between electric vehicles (EVs) and the grid, playing a key role in integrating EVs into smart grids. However, optimizing V2G operations is challenging due to the dynamic nature of energy demand, grid constraints, and user preferences. The paper provides a comprehensive analysis of existing research on V2G optimization and identifies gaps where AI-driven algorithms, machine learning, metaheuristics, and agile optimization can be applied. Case studies and examples demonstrate the effectiveness of AI-driven algorithms in optimizing V2G operations, leading to improved grid stability, cost optimization, and user satisfaction. Agile optimization concepts are introduced to enhance flexibility and responsiveness in V2G optimization. The paper concludes with a discussion on the challenges and future directions for integrating AI-driven methods into V2G systems, highlighting the potential for these intelligent algorithms and methods. V2G systems face several optimization challenges, including managing dynamic energy demand and supply, optimizing EV battery usage while considering user preferences, grid constraints, and environmental factors. These challenges are compounded by uncertainties such as fluctuating electricity prices, unpredictable EV arrival times, and variable renewable energy generation. Traditional optimization methods, such as exact methods and evolutionary algorithms, have been used to address these challenges, but they often suffer from high computational time and limited scalability. AI-based methods, including simheuristics, learnheuristics, and agile optimization, offer promising solutions by enabling real-time adaptation, efficient decision-making, and improved performance in dynamic and uncertain environments. The paper presents a case study on V2G optimization, where the goal is to minimize the cost of charging EVs. The study compares two scenarios: one where a decision-making system is implemented to optimize charging and discharging based on electricity prices, and another where vehicles are charged in the last hour before departure regardless of price. The results show that the AI-driven heuristic approach significantly reduces costs compared to the passive approach. The heuristic model outperforms the exact method in terms of solution quality and computational efficiency, making it a viable option for large-scale V2G systems. The study also highlights the importance of considering EV battery degradation and user preferences in V2G systems to ensure their long-term sustainability and acceptance. Future research directions include the development of more complex models and the integration of advanced grid management systems to enhance the flexibility and resilience of V2G operations.This paper addresses the optimization challenges in Vehicle-to-Grid (V2G) systems and explores the application of artificial intelligence (AI) methods to solve these challenges. V2G systems enable bidirectional energy flow between electric vehicles (EVs) and the grid, playing a key role in integrating EVs into smart grids. However, optimizing V2G operations is challenging due to the dynamic nature of energy demand, grid constraints, and user preferences. The paper provides a comprehensive analysis of existing research on V2G optimization and identifies gaps where AI-driven algorithms, machine learning, metaheuristics, and agile optimization can be applied. Case studies and examples demonstrate the effectiveness of AI-driven algorithms in optimizing V2G operations, leading to improved grid stability, cost optimization, and user satisfaction. Agile optimization concepts are introduced to enhance flexibility and responsiveness in V2G optimization. The paper concludes with a discussion on the challenges and future directions for integrating AI-driven methods into V2G systems, highlighting the potential for these intelligent algorithms and methods. V2G systems face several optimization challenges, including managing dynamic energy demand and supply, optimizing EV battery usage while considering user preferences, grid constraints, and environmental factors. These challenges are compounded by uncertainties such as fluctuating electricity prices, unpredictable EV arrival times, and variable renewable energy generation. Traditional optimization methods, such as exact methods and evolutionary algorithms, have been used to address these challenges, but they often suffer from high computational time and limited scalability. AI-based methods, including simheuristics, learnheuristics, and agile optimization, offer promising solutions by enabling real-time adaptation, efficient decision-making, and improved performance in dynamic and uncertain environments. The paper presents a case study on V2G optimization, where the goal is to minimize the cost of charging EVs. The study compares two scenarios: one where a decision-making system is implemented to optimize charging and discharging based on electricity prices, and another where vehicles are charged in the last hour before departure regardless of price. The results show that the AI-driven heuristic approach significantly reduces costs compared to the passive approach. The heuristic model outperforms the exact method in terms of solution quality and computational efficiency, making it a viable option for large-scale V2G systems. The study also highlights the importance of considering EV battery degradation and user preferences in V2G systems to ensure their long-term sustainability and acceptance. Future research directions include the development of more complex models and the integration of advanced grid management systems to enhance the flexibility and resilience of V2G operations.