SourcesIntentCUA Multi-Agent Desktop Automation 74.83% SuccessarXiv·high signalMulti-agent framework achieving 74.83% task success rate. Planner, Plan-Optimizer, Critic over shared memory. Cross-application skill transfer. Outperforms RL and trajectory baselines.SourceSource pagearXiv↳ Follow the threadStack layer / Threat patternMCPZoo Study: Scanners Call 96.89% of MCP Servers 'Risky' — But Under Half of Those Alerts Are RealarXivStack layer / Update threadSLBench Finds Up to 70% Unsafe Execution When Codex and Claude Code Follow Logical Relations in Skill FilesarXivStack layer'Who Broke the System?' AgentLocate Pinpoints the Failing Agent and Step in Multi-Agent RunsarXivStack layerStore agent episodes in a dedicated event subgraph and use cross-graph traversal for multi-hop temporal questionsarXiv 2604.12285ContrastShared Selective Persistent Memory Lifts Agentic Task Completion to 96% and Cuts Per-Call Token Cost 97xarXivStack 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 OraclearXivFollow-up threadSurvey: Metacognition in LLMs — foundations, progress, and open problems for self-monitoring agentsarXiv