SourcesSpargeAttention2 — 95% Sparsity 16.2x Attention SpeeduparXiv·high signalTsinghua hybrid Top-k plus Top-p masking with distillation fine-tuning. 95% attention sparsity, 16.2x speedup on video diffusion. arXiv 2602.13515.SourceSource pagearXiv↳ Follow the threadPolicy dependency / Threat patternTool-Grounded LLM Agent 'TerraRepair' Lifts Terraform Security Fix Rates From 26.6% to 78.4%arXivStack layer / Threat patternMCPZoo Study: Scanners Call 96.89% of MCP Servers 'Risky' — But Under Half of Those Alerts Are RealarXivPolicy dependencyNew Paper 'aiAuthZ' Moves Agent Authorization Off-Host, Reports 0% Residual Attack Across 15 LLMsarXivStack 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 / Stack layerCynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write PermissionsIT Security NewsStack layer / Update threadSLBench Finds Up to 70% Unsafe Execution When Codex and Claude Code Follow Logical Relations in Skill FilesarXivSame source domain / Semantic neighborEvidence-Backed Video Question Answering pushes Video LLMs from black-box answers to grounded evidencearXiv