Changing only the consequence-allocation rule in multi-agent AI shifts collective fatality by 22–58 percentage points across seven model populations, with identity salience in rule text causally driving targeted exploitation.
On the nonexistence of a dominant strategy mechanism for making optimal public decisions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety
Changing only the consequence-allocation rule in multi-agent AI shifts collective fatality by 22–58 percentage points across seven model populations, with identity salience in rule text causally driving targeted exploitation.