The field of large language models (LLMs) is rapidly evolving, with a growing focus on integrating these models with human decision-making and strategic reasoning. Recent studies have demonstrated the potential of LLMs to enhance human performance in complex tasks, such as financial analysis and chess playing. The development of frameworks like the Odychess Approach and the Strategy-Augmented Planning framework has shown promising results in improving decision-making and strategic reasoning capabilities. Furthermore, research has highlighted the importance of aligning LLMs with human values and intentions, particularly in high-stakes decision-making scenarios. Noteworthy papers in this area include the introduction of the straQ* framework, which leverages Q-learning to optimize LLM-based decision-making, and the development of the DSADF framework, which integrates LLMs with reinforcement learning agents to achieve more efficient and adaptive decision-making. Overall, the current trend in this field is towards developing more sophisticated and human-like LLMs that can effectively interact with humans and enhance their decision-making capabilities.