MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials

תקציר מקורי באנגליתarXiv:2609.08399v1 Announce Type: new Abstract: Universal machine-learning interatomic potentials (u-MLIPs) aim to generalize across diverse configurations. Benchmarks enable reproducible evaluation but may not expose failures outside their predefined scope. Here, we show that physics-informed search can complement benchmark-based evaluation by uncovering hidden failure modes. We introduce MLIP Detective, an agentic framework for active failure mode discovery. Starting from benchmark evidence, MLIP Detective generates falsifiable, physics-informed failure hypotheses, screens them with inexpensive simulations, and escalates only the most suspicious cases to human experts together with proposed verification protocols. Without issue-specific prompting, MLIP Detective identified and characteri