The field of social-ecological systems modeling is moving towards increased integration of large language models (LLMs) and empirical game-theoretic analysis (EGTA). This shift enables the development of more sophisticated models that capture heterogeneity, uncertainty, and strategic interaction in complex systems. Recent work has highlighted the importance of methodological diversity in LLM-augmented frameworks, as well as the need to consider population-level effects when deploying LLM-based systems at scale. The study of emergent coordinated behaviors in networked LLM agents has also become a key area of research, with implications for understanding the dynamics of information operations and social media mobilization. Notable papers in this area include:

• One paper that compared four LLM-augmented frameworks and evaluated them on a real-world case study, demonstrating the value of methodological diversity.
• Another paper that systematically explored the effects of group size on multi-agent dynamics, revealing model-dependent dynamical regimes.
• A study that presented the first systematic study of emergent coordination among generative agents in simulated information operations campaigns, highlighting the societal risks posed by increasingly automated, self-organizing information operations.