ResearchIMMACULATE LLM Auditing Framework Detects Model Substitution and Token OverbillingarXiv·high signalXBlueskyLinkedInCopy linkDetects provider model substitution, quantization abuse, and token overbilling via verifiable computation. Relevant to distillation detection trend.SourceSource pagearXiv↳ Follow the threadPolicy dependency / Stack layerBuild Integration, Not Fuzzing, Is What Kills LLM Dynamic Analysis on Real Autonomous-Vehicle StacksarXiv 2608.13450Stack layer / Threat patternTwo-Tier 'Librarian + Writer' Architecture Removes 6,845 Cross-Section Contradictions From LLM Research Reports to ZeroarXiv 2608.12984Stack layer / Threat patternCoins: Evaluating LLM Formal Specifications by Instantiating Them on Trusted Test Cases Instead of Proving EquivalencearXiv 2608.13077Stack layer / Threat patternFormal Specs Inferred From Tests Alone, Without White-Box Access to the ImplementationarXiv 2608.13240Stack layer / Threat patternCrEST: let the teacher set the magnitude of the update, not the direction, for multi-turn tool-use agentsarXivStack layer / Threat patternInterSAGE Proposes the Trust Layer MCP, A2A and ANP Left Out of the Internet of AgentsarXiv 2608.13030Stack layer / Threat patternLycheeMemory V2 Consolidates Agent Memory at Semantic Segment Level, Not Per Turn: 92.20% on LongMemEval-S With 75.9% Fewer Construction TokensarXiv (via HuggingFace Daily Papers)Stack layer / Threat patternTwo Copies of the Same Model Co-Fail on 90% of Missions — Redundancy Math for Agents Is BrokenarXiv 2608.12895