When agents work together, when they fail to, and when working together turns against the people they serve.
Open questions
Papers
- Vallinder Hughes 2024 - Cultural evolution of cooperation
- Horibe Itao Toyokawa 2026 - Reputation-based cooperation
- Piatti et al 2024 - Cooperate or collapse
- Dafoe et al 2020 - Open problems in cooperative AI
- Hammond et al 2025 - Multi-agent risks from advanced AI
- Akata et al 2025 - Playing repeated games with LLMs
- Li Shirado 2025 - Spontaneous giving and calculated greed
- Willis et al 2026 - Collective behaviour of hundreds of agents
- Motwani et al 2024 - Secret collusion
- Fish Gonczarowski Shorrer 2024 - Algorithmic collusion by LLMs
- Nakamura et al 2026 - Colosseum
- Rippin et al 2026 - Tool use enables undetectable steganography
- Shi Zhang Yang 2026 - Emergent collusion in long-horizon interaction
- Bracale Syrnikov et al 2026 - Institutional AI
- Rose et al 2026 - Detecting collusion through interpretability
- Schroeder de Witt et al 2025 - Open challenges in multi-agent security
- Tomasev et al 2025 - Virtual agent economies
- Bansal et al 2025 - Magentic Marketplace
- Anthropic 2026 - Patterns and problems in multiagent systems
- Kundu et al 2026 - Similarity signals induce cooperation
- Ferraz de Arruda et al 2026 - Cooperation without individual fidelity
People
Placed by the editor, v1 — corrections welcome.