Multi-agent free-energy minimization under bounded rationality and local information yields approximate Nash equilibria, with cooperative games represented variationally as Gibbs distributions over coalitions and a free-energy version of the Harsanyi dividend for synergy.
Neu- rogame transformer: Gibbs-inspired attention driven by game theory and statistical physics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Attention heads exhibit negative higher-order synergy (negative triple dividends), allowing pruning of redundant heads that cuts FLOPs by ~18% with only small perplexity increase.
citing papers explorer
-
A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics
Multi-agent free-energy minimization under bounded rationality and local information yields approximate Nash equilibria, with cooperative games represented variationally as Gibbs distributions over coalitions and a free-energy version of the Harsanyi dividend for synergy.
-
A Game Theoretic Free Energy Analysis of Higher Order Synergy in Attention Heads of Large Language Models
Attention heads exhibit negative higher-order synergy (negative triple dividends), allowing pruning of redundant heads that cuts FLOPs by ~18% with only small perplexity increase.