A folk theorem for LLMs proves that all feasible and individually rational outcomes can be sustained as ε-equilibria in repeated games where LLMs advise client populations, despite indirect observation.
(b) probabilityp: probe (=test move): uniformly select an extreme meta-action fromtM a:aPAu
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sustaining Cooperation in Populations Guided by AI: A Folk Theorem for LLMs
A folk theorem for LLMs proves that all feasible and individually rational outcomes can be sustained as ε-equilibria in repeated games where LLMs advise client populations, despite indirect observation.