{
  "schema_version": "1.1",
  "id": "archive:https://arxiv.org/abs/2610.35868v1",
  "slug": "2610-35868v1-1uzxrmk",
  "url": "https://feed7.dev/p/2610-35868v1-1uzxrmk",
  "title": "Retriever-Free Retrieval: Navigating Documents with Decision Models",
  "why_included": "DecisionRAG uses an LLM to navigate document branches without a first-stage retriever. Its reported gains suggest retrieval quality can improve by changing how candidates are searched, not only how they are ranked.",
  "summary": "DecisionRAG uses a language model to choose which branches of a corpus to explore, then narrows from broad topics to passages. It generates no tokens during these decisions and requires no task-specific training or first-stage retriever. Across four benchmarks, it ran in **0.7–1.8 seconds** per query, including on **2.68 million** Wikipedia paragraphs.",
  "practical_implication": "If your agent depends on retrieval, this points to a possible alternative to lexical or embedding search followed by reranking: use a decision model to guide corpus navigation. The reported comparison beat dense retrieval with an 8B reranker by **13.8 R@1 points** on MultiDoc2Dial and **17.4 Hit@1 points** on Natural Questions.",
  "agent_context": "DecisionRAG uses a language model to choose which branches of a corpus to explore, then narrows from broad topics to passages. It generates no tokens during these decisions and requires no task-specific training or first-stage retriever. Across four benchmarks, it ran in **0.7–1.8 seconds** per query, including on **2.68 million** Wikipedia paragraphs.\n\nIf your agent depends on retrieval, this points to a possible alternative to lexical or embedding search followed by reranking: use a decision model to guide corpus navigation. The reported comparison beat dense retrieval with an 8B reranker by **13.8 R@1 points** on MultiDoc2Dial and **17.4 Hit@1 points** on Natural Questions.\n\nThese are paper results, and the material does not describe a production implementation or its deployment costs. It remains open how well this approach transfers to other corpora and workloads.",
  "source": {
    "name": "arXiv",
    "url": "https://arxiv.org/abs/2610.35868v1",
    "published_at": "2026-10-26T17:59:44.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Paper",
  "layer": "context",
  "domains": [
    "research",
    "data"
  ],
  "topics": [
    "retrieval",
    "context-engineering"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "These are paper results, and the material does not describe a production implementation or its deployment costs. It remains open how well this approach transfers to other corpora and workloads."
  ],
  "connected_context": {
    "meaning": "DecisionRAG presents corpus navigation as an alternative retrieval route: a model selects branches and passages without a first-stage retriever. Its reported benchmark results make it a candidate to compare with existing pipelines, while the supplied work on chunking, memory, and persistent knowledge shows that retrieval quality and cost remain workload- and architecture-dependent.",
    "corpus_size": 928,
    "generated_at": "2026-10-27T11:06:40.967Z",
    "connections": [
      {
        "title": "Stop Chunking Like It's 2022 — Yuval Belfer, AI21 Labs",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=r9OwPx_HoV0",
        "feed7_url": "https://feed7.dev/p/stop-chunking-like-it-s-2022-yuval-belfer-ai21-labs-1bsztja",
        "reason": "Both challenge a fixed retrieval pipeline: DecisionRAG replaces the first-stage retriever with guided navigation, while multiscale indexing changes chunk granularity and fusion."
      },
      {
        "title": "Graphify-Labs/graphify",
        "source_name": "GitHub",
        "source_url": "https://github.com/Graphify-Labs/graphify",
        "feed7_url": "https://feed7.dev/p/graphify-1e0bs1f",
        "reason": "Graphify exposes repository relationships as a queryable graph; DecisionRAG’s branch navigation offers a different way to narrow a corpus before selecting relevant evidence."
      },
      {
        "title": "nashsu/llm_wiki",
        "source_name": "GitHub",
        "source_url": "https://github.com/nashsu/llm_wiki",
        "feed7_url": "https://feed7.dev/p/llm-wiki-1dqmknq",
        "reason": "LLM Wiki compiles sources into persistent, traceable pages, whereas DecisionRAG navigates the corpus at query time; the approaches differ in when and how retrieved context is organized."
      },
      {
        "title": "Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2608.02560v1",
        "feed7_url": "https://feed7.dev/p/2608-02560v1-1u8ls14",
        "reason": "PRECOG stores reusable corpus states for compatible SSMs to reduce repeated ingestion, while DecisionRAG chooses passages through query-time navigation; their gains depend on different model and deployment constraints."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-10-26T17:59:44.000Z",
  "modified_at": "2026-10-26T17:59:44.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/2610-35868v1-1uzxrmk",
    "json": "https://feed7.dev/p/2610-35868v1-1uzxrmk.json",
    "markdown": "https://feed7.dev/p/2610-35868v1-1uzxrmk.md"
  }
}