SourcesPyVision-RL Solving Agent Interaction CollapsearXiv·medium signalAddresses RL-trained agents learning to reduce tool usage. Oversampling-filtering-ranking rollout strategy sustains interaction.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 ItselfarXivFollow-up threadSurvey: Metacognition in LLMs — foundations, progress, and open problems for self-monitoring agentsarXivStack layer / ContrastBackendForge: Best Coding Agent (GPT-5.5) Deploys Correct Backends Only 28.6% of the Time Under a Strict OraclearXivStack 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 NewsPolicy dependency / Threat patternTool-Grounded LLM Agent 'TerraRepair' Lifts Terraform Security Fix Rates From 26.6% to 78.4%arXivStack layer / Threat patternStudy of 44 Developers: AI Code Assistants Barely Improve Secure API UsagearXivStack layer / Update threadAgentLens: Open-Source Benchmark Scores the Whole Coding-Agent Trajectory, Not Just Pass/FailarXiv