ResearchAgentic Critical Training — Why Actions Succeed Not Just What To DoarXiv·high signalNew training paradigm contrasting successful against suboptimal actions. Quality judgment as first-class training objective.SourceSource pagearXiv↳ Follow the threadStack layer / Threat patternMako: A 'Self-Evolving Agentic OS' That Writes New Exploits Against Live Targets and Hot-Loads Them Into ItselfarXivStack layer / ContrastBackendForge: Best Coding Agent (GPT-5.5) Deploys Correct Backends Only 28.6% of the Time Under a Strict OraclearXivPolicy dependency / ContrastNetInjectBench: Naive Network-Ops Agents Take Unsafe Actions 82.5% of the Time Under Prompt InjectionarXivPolicy dependency / Stack layerVerification is now harder than generation for coding agents — budget accordinglyarXiv 2606.26300Contrast / Update threadMetaPerch: Training Bioacoustics Foundation Models on Citizen-Science Metadata, Not Just AudioarXivStack layer / Threat patternMCPZoo Study: Scanners Call 96.89% of MCP Servers 'Risky' — But Under Half of Those Alerts Are RealarXivStack layer / Threat patternPlausible Deniability Guarantees for Whistleblowers: A Formal Privacy Framework for Anonymous ReportingarXivContrastExplainable Agentic Detector Flags Conversational Scams at 97.8% AccuracyarXiv