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 threadPolicy dependency / Update threadNetInjectBench: Naive Network-Ops Agents Take Unsafe Actions 82.5% of the Time Under Prompt InjectionarXivStack layerDistributed Backdoors Prove Per-Step Agent Monitors Can Be Right on Every Step and Still Miss the AttackarXivStack layerAria: A General Code Agent + Verification Harness Proves All 4,257 Core Iris Lemmas Fully AutomaticallyarXivStack 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 ItselfarXivStack layer / Threat patternMCPZoo Study: Scanners Call 96.89% of MCP Servers 'Risky' — But Under Half of Those Alerts Are RealarXivContrastHow 20 Practitioners Actually Build SE Agents: A Mixed-Methods Study of the Undocumented CraftarXivStack layer / ContrastBackendForge: Best Coding Agent (GPT-5.5) Deploys Correct Backends Only 28.6% of the Time Under a Strict OraclearXiv