{
  "annotation_id": "8f550aec-09e0-422c-a930-c7139c45f5fa",
  "date_created": "2026-02-17T05:53:20.333000Z",
  "date_modified": "2026-02-17T05:53:20.333000Z",
  "file_hash": "891dba28ea2a573c07ffc7e7cc7a732a5793bd01faf8928a9b02f30ffc59b70b",
  "private": false,
  "record": {
    "abstract": "Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge. Recently, some works have incorporated iterative knowledge accumulation processes into RAG models to progressively accumulate and refine query-related knowledge, thereby constructing more comprehensive knowledge representations. However, these iterative processes often lack a coherent organizational structure, which limits the construction of more comprehensive and cohesive knowledge representations. To address this, we propose PAGER, a page-driven autonomous knowledge representation framework for RAG. PAGER first prompts an LLM to construct a structured cognitive outline for a given question, which consists of multiple slots representing a distinct knowledge aspect. Then, PAGER iteratively retrieves and refines relevant documents to populate each slot, ultimately constructing a coherent page that serves as contextual input for guiding answer generation. Experiments on multiple knowledge-intensive benchmarks and backbone models show that PAGER consistently outperforms all RAG baselines. Further analyses demonstrate that PAGER constructs higher-quality and information-dense knowledge representations, better mitigates knowledge conflicts, and enables LLMs to leverage external knowledge more effectively. All code is available at https://github.com/OpenBMB/PAGER.",
    "arxiv_id": "2601.09402",
    "authors": [
      "Xinze Li",
      "Zhenghao Liu",
      "Haidong Xin",
      "Yukun Yan",
      "Shuo Wang",
      "Zheni Zeng",
      "Sen Mei",
      "Ge Yu",
      "Maosong Sun"
    ],
    "categories": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "title": "Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation",
    "url": "https://arxiv.org/abs/2601.09402",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "1cf28597-1275-4cb9-bace-bf293d4acd45",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}