This paper introduces an advanced intelligent crop management system that combines deep reinforcement learning (RL), language models (LMs), and crop simulations facilitated by the Decision Support System for Agrotechnology Transfer (DSSAT). The system aims to optimize crop management practices to maximize yield, economic profitability, and environmental sustainability. By transforming state variables from the simulator into more informative language sentences, the LMs enhance the RL agent's ability to understand and explore optimal management strategies. The empirical results, based on simulations of maize crops in Florida and Zaragoza, demonstrate that the LM-based RL agent outperforms baseline methods, achieving over 49% improvement in economic profit and reduced environmental impact. The study also highlights the adaptability of the framework to different reward functions, balancing crop yield, resource utilization, and environmental impact. The research contributes to the field by exploring the potential of LMs in crop management and advancing the state of intelligent crop management systems.This paper introduces an advanced intelligent crop management system that combines deep reinforcement learning (RL), language models (LMs), and crop simulations facilitated by the Decision Support System for Agrotechnology Transfer (DSSAT). The system aims to optimize crop management practices to maximize yield, economic profitability, and environmental sustainability. By transforming state variables from the simulator into more informative language sentences, the LMs enhance the RL agent's ability to understand and explore optimal management strategies. The empirical results, based on simulations of maize crops in Florida and Zaragoza, demonstrate that the LM-based RL agent outperforms baseline methods, achieving over 49% improvement in economic profit and reduced environmental impact. The study also highlights the adaptability of the framework to different reward functions, balancing crop yield, resource utilization, and environmental impact. The research contributes to the field by exploring the potential of LMs in crop management and advancing the state of intelligent crop management systems.