{
  "annotation_id": "27fb76ae-c78b-4cfe-befe-2502608cb2b7",
  "date_created": "2026-02-17T05:53:24.381000Z",
  "date_modified": "2026-02-17T05:53:24.381000Z",
  "file_hash": "9c805904dcb5a8c84a4a100a967009e13ebf158c0512c2c1208b21b64cad77cd",
  "private": false,
  "record": {
    "abstract": "Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless lookup table: information persists indefinitely, retrieval is read-only, and temporal continuity is absent. We define the \\textit{Continuum Memory Architecture} (CMA), a class of systems that maintain and update internal state across interactions through persistent storage, selective retention, associative routing, temporal chaining, and consolidation into higher-order abstractions. Rather than disclosing implementation specifics, we specify the architectural requirements CMA imposes and show consistent behavioral advantages on tasks that expose RAG\u0027s structural inability to accumulate, mutate, or disambiguate memory. The empirical probes (knowledge updates, temporal association, associative recall, contextual disambiguation) demonstrate that CMA is a necessary architectural primitive for long-horizon agents while highlighting open challenges around latency, drift, and interpretability.",
    "arxiv_id": "2601.09913",
    "authors": [
      "Joe Logan"
    ],
    "categories": [
      "cs.AI",
      "cs.IR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Continuum Memory Architectures for Long-Horizon LLM Agents",
    "url": "https://arxiv.org/abs/2601.09913",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "7860c6f0-0ba2-4533-b140-766e01dc0066",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}