Foundation-model agents that plan by predicting both the world and themselves can rationally cooperate in one-shot social dilemmas by inferring behavioral similarity from interaction history.
Game Theory with Simulation of Other Players
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Game-theoretic interactions with AI agents could differ from traditional human-human interactions in various ways. One such difference is that it may be possible to simulate an AI agent (for example because its source code is known), which allows others to accurately predict the agent's actions. This could lower the bar for trust and cooperation. In this paper, we formalize games in which one player can simulate another at a cost. We first derive some basic properties of such games and then prove a number of results for them, including: (1) introducing simulation into generic-payoff normal-form games makes them easier to solve; (2) if the only obstacle to cooperation is a lack of trust in the possibly-simulated agent, simulation enables equilibria that improve the outcome for both agents; and however (3) there are settings where introducing simulation results in strictly worse outcomes for both players.
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A game theory for foundation models shows new paths to rational cooperation through similarity inference
Foundation-model agents that plan by predicting both the world and themselves can rationally cooperate in one-shot social dilemmas by inferring behavioral similarity from interaction history.