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.
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence , articleno =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A theoretical attacker-defender game in LLM adversarial prompting yields a best-response attack related to existing methods, reveals attacker advantages at equilibrium, and derives a provably optimal defense with stronger empirical performance.
ETI lets LLM agents infer and track partners' psychological traits (warmth and competence) from histories, cutting payoff loss 45-77% in games and boosting performance 3-29% on MultiAgentBench versus CoT baselines.
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.
-
A Theoretical Game of Attacks via Compositional Skills
A theoretical attacker-defender game in LLM adversarial prompting yields a best-response attack related to existing methods, reveals attacker advantages at equilibrium, and derives a provably optimal defense with stronger empirical performance.
-
Explicit Trait Inference for Multi-Agent Coordination
ETI lets LLM agents infer and track partners' psychological traits (warmth and competence) from histories, cutting payoff loss 45-77% in games and boosting performance 3-29% on MultiAgentBench versus CoT baselines.