A graph-based propagation model for error cascades in LLM multi-agent systems plus a genealogy-graph governance plugin that prevents final infection in at least 89% of runs across tested frameworks.
Epidemic processes in complex networks.Reviews of modern physics, 87(3):925–979, 2015
2 Pith papers cite this work. Polarity classification is still indexing.
verdicts
UNVERDICTED 2representative citing papers
Symmetric one-to-one inter-layer connections promote intra-layer synchronization and remnant memory more reliably than asymmetric random connections, yet asymmetric links better suppress amplitude death at low coupling strengths and frequency mismatches.
citing papers explorer
-
From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
A graph-based propagation model for error cascades in LLM multi-agent systems plus a genealogy-graph governance plugin that prevents final infection in at least 89% of runs across tested frameworks.
-
Trade-Off Between Multiplicity and Specificity in the Inter-layer Connectivity of non-identical Multilayer Networks
Symmetric one-to-one inter-layer connections promote intra-layer synchronization and remnant memory more reliably than asymmetric random connections, yet asymmetric links better suppress amplitude death at low coupling strengths and frequency mismatches.