{"type":"link","version":"1.0","title":"Agent success on long-horizon tasks is often stochastic: pass@3 reliability is roughly 60% of pass@1 rate","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/clinical-agent-stochasticity-collapses-reliability","thumbnail_url":"https://ai-arch.pages.dev/og/clinical-agent-stochasticity-collapses-reliability.png","thumbnail_width":1200,"thumbnail_height":630}