Coverage Aware Active Evaluation for Failure Discovery with Paired Systems

arXiv cs.AIAugust 17, 2026en

arXiv:2608.13719v1 Announce Type: new Abstract: Autonomous systems can fail in rare and heterogeneous ways, making real-world failure discovery difficult under limited testing budgets. Although cheaper proxies such as simulators, lower-fidelity systems, or related policies can be sampled extensively to find failures, proxy failures often do not transfer to the real world due to sim-to-real and system-to-system gaps. The key challenge is therefore to effectively leverage proxy system information for accurate prediction of severe target system failures. We propose an adaptive failure discovery method that combines proxy evaluations with limited target system results to guide scenario selection

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Företag