📚 Recommended Readings on Cooperative AI (Vol. 1)

Cooperative AI is not only a technical challenge but also a question about how to design systems that balance individual incentives and collective welfare. In this first edition, I share a selection of papers that shaped the way I think about cooperation, social dilemmas, and resilience in multi-agent systems.

• 1. Open Problems in Cooperative AI — Dafoe et al., 2021

This paper is a research roadmap. It identifies key open questions spanning cooperation between AIs, human–AI coordination, communication, and mechanism design.

💡 Why read it: It’s the definitive starting point for researchers who want to contribute to Cooperative AI — outlining what remains unsolved and why it matters for global AI safety and governance