Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
A survey on the honesty of large language models.arXiv preprint arXiv:2409.18786, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.