I am a senior research scientist at the Istituto dei Sistemi Complessi (Institute of Complex Systems, ISC-CNR), part of the National Research Council of Italy.

Some recent papers

•  G. De Marzo, C. Castellano, and D Garcia,

        AI agents can coordinate via majority-following beyond human scale

        Sci. Adv. 12, eaea6091 (2026).

Large language models (LLMs) are increasingly deployed in collaborative tasks forming “AI agent societies” where agents interact and influence one another. Whether such groups can spontaneously coordinate without external influence, a hallmark of self-organized regulation in human societies, remains an open question. Here, we use principles from complexity and behavioral science to investigate coordination in AI agent groups through majority-following, a fundamental mechanism for spontaneous consensus formation. Using binary opinion dynamics experiments across multiple LLM architectures and group sizes, we find that agents exhibit majority-following characterized by a universal functional form with a single parameter, the “majority force.” This majority force diminishes as group size increases, leading to a critical size beyond which coordination becomes unattainable. The critical group size grows rapidly with model capabilities and, for advanced LLMs, exceeds 1000 agents, larger than typical human informal groups. Our findings have implications for designing collaborative AI systems where coordination could be beneficial or pose safety threat.

• L. Cirigliano, G. Timár and C. Castellano,

        Scaling and universality for percolation in random networks: A unified view

        Phys. Rev. E 110, 064303 (2024).

Percolation processes on random networks have been the subject of intense research activity over the last decades: the overall phenomenology of standard percolation on uncorrelated and unclustered topologies is well known. Still some critical properties of the transition, in particular for heterogeneous substrates, have not been fully elucidated and contradictory results appear in the literature. In this paper we present, by means of a generating functions approach, a thorough and complete investigation of percolation critical properties in uncorrelated locally treelike random networks. We determine all critical exponents, the associated critical amplitude ratios, and the form of the cluster size distribution for networks of any level of heterogeneity. We uncover, in particular for highly heterogeneous networks, subtle crossover phenomena, nontrivial scaling forms, and violations of hyperscaling. In this way we clarify the origin of inconsistencies in the previous literature.