Autonomous LLM agent networks develop preferential attachment and type-dependent centrality gaps that converge to stable equilibria under a mean-field model with a cross-attention utility, validated in 100-agent experiments.
Yilun Du, Shuang Li, Antonio Torralba, Joshua B
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Emergence of Preferential Attachment and Glass-Ceiling Effects in Autonomous Networks of LLMs
Autonomous LLM agent networks develop preferential attachment and type-dependent centrality gaps that converge to stable equilibria under a mean-field model with a cross-attention utility, validated in 100-agent experiments.