SourcesAdversarial Intent Latent Variable Stateful Trust for Agentic RAGarXiv·high signalXBlueskyLinkedInCopy linkPOMDP framework for agent security. MMA-RAG Trust Agent achieves 6.5x attack success rate reduction. Most rigorous agent defense paper this week.SourceSource pagearXiv↳ Follow the threadPolicy dependency / Stack layerRIPPLE: an edit confined to one prompt-policy segment changes downstream behavior, so replay candidate edits after previously accepted ones before persistingarXiv 2609.12127Stack layer / Threat patternTwo-gap framework recasts reward hacking and hallucination as symptoms of requirement and model gapsarXivPolicy dependency / Stack layerCodeBLEU Scored 91% for Both RAG Strategies While One of Them Hallucinated APIs 56.4% of the TimearXiv 2609.12464Stack layer / Threat patternSplitting a CTF Task Into Isolated Sub-Contexts Lets a Local gemma-4 Solve 18.52% of Challenges Standard Agent Loops FailarXiv 2609.12839Policy dependency / Threat patternAn audit of a production agent pipeline found a reported p99 latency of 2,147,483,647 ms, the signed 32-bit maximum, from a lifecycle clamparXiv 2609.12017Stack layer / Threat patternMarket Concentration Barely Changes Model Collapse: Pushing One Model to 90% Share Moves Five-Generation Endpoints a Few PercentarXiv 2609.11146Policy dependency / Threat patternMOSAIC Picks a GraphRAG Traversal Policy per Query and Beats the Best Fixed Policy by 9.96 PointsarXiv 2609.11065Stack layer / Threat patternAn Unlearning Audit of 263 Released Checkpoints Finds 47 Move Past Their Own Seed Spread Just by Refitting Batch-Norm StatisticsarXiv 2609.11490