ResearchSelf-Healing Router Graph Based Fault Tolerant Tool RoutingarXiv·high signal93% reduction in control-plane LLM calls via graph-based tool routing with auto-recovery. Matches ReAct correctness across 19 scenarios.SourceSource pagearXiv↳ Follow the threadStack layer / Update threadSLBench Finds Up to 70% Unsafe Execution When Codex and Claude Code Follow Logical Relations in Skill FilesarXivPolicy dependency / Update threadNetInjectBench: Naive Network-Ops Agents Take Unsafe Actions 82.5% of the Time Under Prompt InjectionarXivStack layer / ContrastLong-Horizon-Terminal-Bench: Best Frontier Agent Clears Just 15% of Real Terminal Tasks, Mean 4.3%arXiv (Tencent Hunyuan) / HuggingFace Daily PapersStack layerDistributed Backdoors Prove Per-Step Agent Monitors Can Be Right on Every Step and Still Miss the AttackarXivStack 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 2604.12285Stack layer / Threat patternMako: A 'Self-Evolving Agentic OS' That Writes New Exploits Against Live Targets and Hot-Loads Them Into ItselfarXivContrastShared Selective Persistent Memory Lifts Agentic Task Completion to 96% and Cuts Per-Call Token Cost 97xarXiv