HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence

Quick summary

arXiv:2610.02920v1 Announce Type: new Abstract: Agent harnesses play a critical role in defenses by enforcing safety constraints to prevent unsafe actions. However, rapidly emerging attacks outpace manual harness adaptation, motivating automated harness evolution. Yet the signals available for harness evolution are often sparse, such as brief descriptions or a few attack examples in threat reports and preprints. To address this limitation, we introduce HASTE, a multi-agent framework that evolves agent harnesses from sparse threat evidence through an adversarial interplay between safety-specifi