Atlas / Sociology of AI / Paper

Collective cooperation without individual fidelity in LLM agents

Cooperation & CollusionNorms & Culture

Henrique Ferraz de Arruda, Carlos Gracia Lázaro, Alberto Aleta, Yamir Moreno · 2026 · arXiv

Read the source

The best model reproduced aggregate human cooperation curves but not individual differences or decision rules — a warning against validating agent societies only at the group level.

Questions it bears on

Help improve this map

Know a paper that belongs here, or think something needs correcting?

Suggest a correction ↗Contributions are reviewed before they appear.