AI RESEARCH
AgenticRS-EnsNAS: Ensemble-Decoupled Self-Evolving Architecture Search
arXiv CS.LG
•
ArXi:2603.20014v1 Announce Type: new Neural Architecture Search (NAS) deployment in industrial production systems faces a fundamental validation bottleneck: verifying a single candidate architecture pi requires evaluating the deployed ensemble of M models, incurring prohibitive O(M) computational cost per candidate. This cost barrier severely limits architecture iteration frequency in real-world applications where ensembles (M=50-200) are standard for robustness. This work