Language model agents cooperate more in a prisoner's dilemma when repeated interactions and inter-team competition are combined, but only for some models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Super-additive Cooperation in Language Model Agents
Language model agents cooperate more in a prisoner's dilemma when repeated interactions and inter-team competition are combined, but only for some models.