mlsanityData to 14 Oct 2026

Memory-Orchestrated Semantic System (MOSS): An Auditable Agentic Memory Architecture

arXiv 2607.04391 ↗First posted 5 Jul 2026cs.CLcited by 0

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Long-term memory remains a structural weakness of AI agents. The dominant approach, retrieval-augmented generation (RAG), relies on embedding-based similarity search, which is opaque by construction, difficult to audit, and bounded by the theoretical limits of vector representations. We present the Memory-Orchestrated Semantic System (MOSS), an agentic memory architecture in which the agent drives retrieval over a structured relational database. MOSS is model-agnostic, storage-agnostic, and API-agnostic: it runs on any relational engine, connects to any LLM provider (or to deterministic non-LLM processes), and deploys on any infrastructure, local or cloud. Its retrieval execution is symbolic and reproducible (once a query is formulated, no LLM participates in the retrieval loop) and every step of the system, from indexing to answer formulation, is logged and inspectable, making MOSS auditable by construction. Rather than imposing an external ontology, MOSS derives its conceptual vocabulary from the corpus itself. We report on a longitudinal deployment unique in the agentic-memory literature: a year of continuous production over an individual scholar's working corpus--a conversational corpus reaching back to October 2024 (some 44 million tokens, retroactively indexed) comprising 110,183 segments, alongside 163,494 catalogued documents, 569 inductively derived concepts, 322,662 concept annotations, and eleven metadata graphs totaling approximately five million relations--across four successive infrastructure generations. While the present case is that of a single researcher, the architecture is in no way specific to one person: it serves a team, an institution, or any entity that accumulates knowledge over time. We argue that auditable, sovereign, structurally unbounded memory is a precondition for AI agents intended to accompany a person or an organization over years rather than sessions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 31 of its 61 references that are in the map. First posted on arXiv 5 Jul 2026.

Builds on

31 of 61 references.

Closest ancestors · 12

Same direction, newest first

  1. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers8 Mar
  2. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations22 Feb
  3. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applications5 Feb
  4. 2026Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation2 Feb
  5. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents5 Jan
  6. 2025Memory in the Age of AI Agents15 Dec
  7. 2025PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents20 Jun
  8. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  9. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  10. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  11. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  12. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 19

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  3. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  4. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  5. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  6. 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 104
  7. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  8. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 56
  9. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 52
  10. 2023Survey of Vector Database Management Systemscited by 39
  11. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  12. 2026AgentSM: Semantic Memory for Agentic Text-to-SQLcited by 14
7 more
  1. 2025RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledgecited by 13
  2. 2026SuperLocalMemory: Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory Poisoningcited by 7
  3. 2026On Strengths and Limitations of Single-Vector Embeddingscited by 4
  4. 2026AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysiscited by 4
  5. 2026Scaling Laws for Embedding Dimension in Information Retrievalcited by 2
  6. 2026Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detectorcited by 2
  7. 2026Scaling Laws for Agent Harnesses via Effective Feedback Computecited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
  2. 2026SwiftMem: Fast Agentic Memory via Query-aware Indexing
  3. 2026ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Context
  4. 2026Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
  5. 2025Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning
  6. 2026Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
  7. 2026AMA: Adaptive Memory via Multi-Agent Collaboration
  8. 2026Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents