Ilya Horiguchi, Takahide Yoshida, Takashi Ikegami

Recent advancements in Large Language Models (LLMs) have spurred a surge of interest in leveraging these models for game-theoretical simulations, where LLMs act as individual agents engaging in social interactions. This study explores the potential for LLM agents to spontaneously generate and adhere to normative strategies through natural language discourse, building upon the foundational work of Axelrod’s metanorm games. Our experiments demonstrate that through dialogue, LLM agents can form complex social norms, such as metanorms-norms enforcing the punishment of those who do not punish cheating-purely through natural language interaction. The results affirm the effectiveness of using LLM agents for simulating social interactions and understanding the emergence and evolution of complex strategies and norms through natural language. Future work may extend these findings by incorporating a wider range of scenarios and agent characteristics, aiming to uncover more nuanced mechanisms behind social norm formation.

Read the full article at: arxiv.org

Society is reaching a tipping point. The future remains not only uncertain but also seemingly unpredictable, however, using the science of self-organised criticality, the phenomenon describing how small events can create large ripples in networks, this may no longer be the case. In this piece, Dan Braha presents his physics-informed model of civil unrest and shows not only how we can use it to forecast riots and violent disorder, but how in using the ideas of self-organized criticality smaller movements can better work to topple oppressive regimes.

Read the full article at: iai.tv

Claudio Caprioli, Saumitra Kulkarni, Federico Battiston, Iacopo Iacopini, Andrea Santoro, Vito Latora

Investigating how different ingredients are combined in popular dishes is crucial to reveal the fundamental principles behind the formation of food preferences. Here, we use data from food repositories and network analysis to characterize worldwide cuisines. In our framework, each cuisine is represented as a network, where nodes correspond to ingredient types and weighted links describe how frequently pairs of ingredient types appear together in recipes. The networks of ingredient combinations reveal cuisine-specific patterns, highlighting similarities and differences in gastronomic preferences across different world regions. We find that popular ingredients, recurrent combinations, and the way they are organized within the backbone of the network provide a unique fingerprint for each cuisine. Hence, we demonstrate that networks of ingredient combinations are able to cluster global cuisines into meaningful geo-cultural groups, and can also be used to train models to uniquely identify a cuisine from a subset of its recipes. Our study advances our understanding of food combinations and helps uncover the geography of taste, paving the way for the creation of new and innovative recipes.

Read the full article at: arxiv.org

Bibandhan Poudyal , Diogo Pacheco , Marcos Oliveira , Zexun Chen , Hugo S. Barbosa , Ronaldo Menezes and Gourab Ghoshal

Royal Society Open Science

September 2024 Volume 11Issue 9

Human travelling behaviours are markedly regular, to a large extent predictable, and mostly driven by biological necessities and social constructs. Not surprisingly, such predictability is influenced by an array of factors ranging in scale from individual preferences and choices, through social groups and households, all the way to the global scale, such as mobility restrictions in response to external shocks such as pandemics. In this work, we explore how temporal, activity and location variations in individual-level mobility—referred to as predictability states—carry a large degree of information regarding the nature of mobility regularities at the population level. Our findings indicate the existence of contextual and activity signatures in predictability states, suggesting the potential for a more nuanced approach to estimating both short-term and higher-order mobility predictions. The existence of location contexts, in particular, serves as a parsimonious estimator for predictability patterns even in the case of low resolution and missing data.

Read the full article at: royalsocietypublishing.org