Agentic Microphysics: A Manifesto for Generative AI Safety

Abstract

This paper advances a methodological proposal for safety research in agentic AI. As systems acquire planning, memory, tool use, persistent identity, and sustained interaction, safety can no longer be analysed primarily at the level of the isolated model. Population-level risks arise from structured interaction among agents, through processes of communication, observation, and mutual influence that shape collective behaviour over time. As the object of analysis shifts, a methodological gap emerge

Categories

Framework mappings

Suggested from the entry's categories.

@misc{pierucci2026agentic,
  title = {{Agentic Microphysics: A Manifesto for Generative AI Safety}},
  author = {Federico Pierucci and Matteo Prandi and Marcantonio Bracale Syrnikov and Marcello Galisai and Piercosma Bisconti},
  year = {2026},
  month = apr,
  eprint = {2604.15236},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.15236}
}