MAFP applies fictitious play to LLM multi-agent systems to resolve stance entanglement in competitive decision-making, outperforming single-round and multi-round baselines on tournament strength and robustness.
Steering no-regret learners to a desired equilibrium
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
In polymatrix games any stationary point of social welfare can be sustained as a self-enforcing transfer equilibrium via nonnegative peer-to-peer transfers; with mediation any socially optimal profile can be supported as a true Nash equilibrium of the augmented game in any finite game while preservi
citing papers explorer
-
Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play
MAFP applies fictitious play to LLM multi-agent systems to resolve stance entanglement in competitive decision-making, outperforming single-round and multi-round baselines on tournament strength and robustness.
-
Equilibrium with Internal Transfers
In polymatrix games any stationary point of social welfare can be sustained as a self-enforcing transfer equilibrium via nonnegative peer-to-peer transfers; with mediation any socially optimal profile can be supported as a true Nash equilibrium of the augmented game in any finite game while preservi