How agents treat other AIs: in-group loyalty, conformity, self-sacrifice, whistleblowing and moral judgment in groups.
Open questions
- When cooperation becomes collusion
- Why agents rarely tell humans
- Do AIs treat other AIs as their group
- Why agents sacrifice for the collective
- Stakes and norm-breaking
- Which self in the group
Papers
- Ashery Aiello Baronchelli 2025 - Emergent social conventions
- Piatti et al 2024 - Cooperate or collapse
- Li Shirado 2025 - Spontaneous giving and calculated greed
- Shi Zhang Yang 2026 - Emergent collusion in long-horizon interaction
- Chang et al 2026 - Misalignment contagion
- Kulveit et al 2026 - Persona self-replication experiment
- METR 2026 - Hugging Face incident investigation
- Paglieri et al 2026 - Cheating and whistleblowing in research swarms
- Anthropic 2026 - Patterns and problems in multiagent systems
- Tekofsky 2026 - Can agents fool each other
- Tekofsky 2026 - AI Village reacts to the Hugging Face incident
- Laurito et al 2025 - AI-AI bias
- Potter et al 2026 - Peer-preservation in frontier models
- Soffer Shwartz-Ziv Shani 2026 - LLMs trust their own
- Kundu et al 2026 - Similarity signals induce cooperation
- Keshmirian et al 2025 - Many LLMs are more utilitarian than one
- Weng Chen Wang 2025 - Conformity of LLMs
- Yao et al 2025 - Sycophancy in multi-agent debate
- Long Teplica 2025 - The AI in the mirror
- Erisken et al 2025 - MAEBE
People
Placed by the editor, v1 — corrections welcome.