SourcesAgent Primitives Reusable Building Blocks for Multi-Agent SystemsarXiv·high signalIdentifies three recurring computation primitives in multi-agent systems: Review, Voting/Selection, Planning/Execution as composable blocksSourceSource pagearXiv↳ Follow the threadPolicy dependency / Stack layerReason Less, Verify More: Deterministic Gates Catch a Silent Policy-Violation Failure in Tool-Using AgentsarXivStack layer / Threat patternMitigating Taint-Style MCP Server Vulnerabilities Without Touching Server Code (SPELLSMITH)arXivPolicy dependency / Stack layerStrict data-flow tracking is the only defense that zeroes out ADI — spend its utility cost only on code execution and moneyarXiv 2607.05120Threat pattern / Follow-up threadVEXAIoT: arXiv paper demonstrates autonomous IoT vulnerability exploitation using AI agentsarXivStack layer / Contrast'Resample or Reroute?' Reframes LLM Routing Under Real Budget ConstraintsarXivUpdate thread / Follow-up threadEvoAgentBench: A Benchmark That Isolates Whether Agents Can Turn Past Sessions Into Reusable ProceduresarXivStack layer / ContrastAppend runtime nonces to JSON keys and DOM element IDs — a cheap ADI defense that keeps 83% utilityarXiv 2607.05120Stack layerCache and reuse agent-generated tools instead of regenerating code every request (arXiv 2607.08010, July 9)arXiv 2607.08010