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.
Multi-agent debate for llm judges with adaptive stability detection
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
APE post-trains small language models as single-agent or multi-agent prompt enhancers that improve visual alignment on image generation and editing benchmarks without altering the downstream visual model.
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.
-
Security Considerations for Multi-agent Systems
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
-
APE: Agentic Prompt Enhancer for Image Generation and Editing
APE post-trains small language models as single-agent or multi-agent prompt enhancers that improve visual alignment on image generation and editing benchmarks without altering the downstream visual model.