LLMs show strong primary algorithmic monoculture and strategic adjustment to coordination incentives, but underperform humans in sustaining beneficial heterogeneity.
For each of the three treatments with humans, we aim to collect responses from 100 participants (total = 300)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Games
LLMs show strong primary algorithmic monoculture and strategic adjustment to coordination incentives, but underperform humans in sustaining beneficial heterogeneity.