2 papers
cs.MA2026
Agent Delivery Engineering Predictive Reliability Framework
Dexing Liu
Long-horizon LLM multi-agent systems face reliability risks invisible to infrastructure monitoring. We propose the ADE Predictive Reliability Framework (ADE-PRF), enabling proactiv…
cs.MA2026
Intelligence Entropy Principle and the ADE Stability Engineering Framework
Dexing Liu
As LLM-driven multi-agent systems (MAS) transition from lab to production, system behavior exhibits nonlinear degradation. We introduce the Intelligence Entropy Principle: probabil…