ResearchAgentDropoutV2 Test-Time Rectify-or-Reject Pruning for Multi-Agent SystemsarXiv·high signalTackles cascading errors in multi-agent systems. Test-time pruning framework as active firewall between agent handoffs without retraining.SourceSource pagearXiv↳ Follow the threadStack layer / Threat patternMCPZoo Study: Scanners Call 96.89% of MCP Servers 'Risky' — But Under Half of Those Alerts Are RealarXivPolicy dependency / Stack layerCynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write PermissionsIT Security NewsStack layerDistributed Backdoors Prove Per-Step Agent Monitors Can Be Right on Every Step and Still Miss the AttackarXivStack layerMosaic Cuts Multi-Agent Embodied Planning Latency by Attacking Failed Actions, Not Just CoordinationarXivThreat patternMalaika Grounds Agentic Malware Analysis in Domain, Program Semantics, and Threat IntelarXivStack layer'Coding Agents Think Ahead of Time': Latent Probes Predict Outcomes 25 Steps EarlyarXiv / Hacker NewsStack layerWebDesignIter: Giving Front-End Coding Agents 'Design Knowledge' to Survive Repo-Level IterationarXivStack layer / Threat patternMako: A 'Self-Evolving Agentic OS' That Writes New Exploits Against Live Targets and Hot-Loads Them Into ItselfarXiv