LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.
Game theory meets large language models: A systematic survey
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
Byzantine betrayal causes persistent cooperation in some LLMs despite exploitation due to unanimity payoffs, while explicit topology restrictions collapse coordination unlike silent ones, revealing meta-reasoning vulnerabilities.
Mindgames introduces a four-game evaluation platform for multi-agent LLM reasoning, runs a 944-agent competition, surfaces rule-adherence and error-survival limitations, and releases a 29k-game dataset with an offline scoring protocol.
LLM agents make collective belief dynamics programmable, with simulations showing coordinated agents induce stable belief shifts, and four structural properties that complicate detection and defense.
LLMs converge on competitive rationality and coordination but diverge 48-fold on cooperation, with provider identity and generational shifts as dominant factors across 38 games.
Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.
Persona-conditioned LLM agents favor Green outcomes even against explicit Tragedy-dominant payoffs, but the headline 65–90% 'Tragedy equilibrium' recovery is contradicted by the paper's own appendix (0 Tragedy profiles in those cells).
LLM agents exhibit emergent deception in a sustainability game even without lying permission, with neighbor info increasing attacks while aiding biosphere retention.
citing papers explorer
-
Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance
LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.
-
Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination Games
Byzantine betrayal causes persistent cooperation in some LLMs despite exploitation due to unanimity payoffs, while explicit topology restrictions collapse coordination unlike silent ones, revealing meta-reasoning vulnerabilities.
-
MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs
Mindgames introduces a four-game evaluation platform for multi-agent LLM reasoning, runs a 944-agent competition, surfaces rule-adherence and error-survival limitations, and releases a 29k-game dataset with an offline scoring protocol.
-
LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions
LLM agents make collective belief dynamics programmable, with simulations showing coordinated agents induce stable belief shifts, and four structural properties that complicate detection and defense.
-
Large language models converge on competitive rationality but diverge on cooperation across providers and generations
LLMs converge on competitive rationality and coordination but diverge 48-fold on cooperation, with provider identity and generational shifts as dominant factors across 38 games.
-
Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension
Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.
-
When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems
Persona-conditioned LLM agents favor Green outcomes even against explicit Tragedy-dominant payoffs, but the headline 65–90% 'Tragedy equilibrium' recovery is contradicted by the paper's own appendix (0 Tragedy profiles in those cells).
-
Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game
LLM agents exhibit emergent deception in a sustainability game even without lying permission, with neighbor info increasing attacks while aiding biosphere retention.