## Introduction Conflict resolution is a complex task that requires a deep understanding of the interagent dynamics. However, most conflict analysis studies have focused on trisecting agent pairs, agents, or issues, which contributes to understanding the nature of conflicts but falls short in addressing their resolution. In particular, strategy formulation, as an essential component of conflict resolution and mitigation, has received insufficient scholarly attention. Therefore, this paper aims to explore feasible strategies from two perspectives: consistency and non-consistency. In particular, we begin by computing the overall rating of a clique of agents based on positive and negative similarity degrees. We then consider the weights of both agents and issues and propose weighted consistency and non-consistency measures, which are respectively used to identify the feasible strategies for a clique of agents. Algorithms are developed to identify feasible strategies, L-order feasible strategies, and the corresponding optimal ones. Finally, we apply these models to two commonly used case studies on NBA labor negotiations and development plans for Gansu Province and conduct a sensitivity analysis on parameters and a comparative analysis with existing state-of-the-art conflict analysis approaches. The comparison results demonstrate that our conflict resolution models outperform conventional approaches by unifying weighted agent-issue evaluation with consistency and non-consistency measures to enable the systematic identification of not only feasible strategies but also optimal solutions. ## Technical context Large language models, such as Llama, have been developed for specific tasks, such as answering questions or generating text. However, these models can be used to analyze complex conflicts. Trisecting agent pairs, agents, or issues is a common approach to understanding conflicts, but it may be limiting in resolving conflicts. New language models can help overcome these limitations by using weighted consistency and non-consistency measures. ## Implications The results of this study have significant implications for understanding and resolving complex conflicts. Language models can be used to identify feasible strategies and optimal solutions, which can help reduce conflicts and improve relationships. ## Conclusion In conclusion, this study demonstrates the importance of using large language models to understand and resolve complex conflicts. New language models can help overcome conventional approaches by using weighted consistency and non-consistency measures.