让大模型像思考一样检索：用可编译的维基结构实现智能迭代查证。
Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
- 将知识组织为带双向链接的维基页面，支持搜索、阅读和跳转操作。
- 在多个问答数据集上领先现有方法2.0-8.1个F1分数，多文档查询表现突出。
- 适合需要深度推理与持续纠错的智能代理系统，尤其擅长复杂多步检索。
大模型代理需将检索从一次性查找转变为类推理行为：搜索、阅读、跳转并判断证据是否充分。然而当前检索增强生成（RAG）系统将外部知识视为扁平文本块，仅通过嵌入相似性检索，难以支持迭代式推理。本文提出LLM-Wiki，一种面向代理的检索系统，将外部知识构建成可编译、可组合且自我演进的结构，而非静态索引。该系统将文档编译为带有双向链接的结构化维基页面，通过标准工具调用接口暴露搜索、阅读与链接跳转能力，并引入错误簿实现持久化的结构与语义自我修正。在HotpotQA、MuSiQue和2WikiMultiHopQA上，LLM-Wiki达到最优性能，相比HippoRAG 2、LightRAG和GraphRAG提升2.0-8.1 F1分。在AuthTrace上，整体准确率最佳，尤其在多文档结构化查询任务中优势显著，验证了基于编译的检索可泛化至非链式多跳推理场景。
原文摘要 · Abstract (English)
LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when evidence is sufficient. Yet current Retrieval-Augmented Generation (RAG) systems organize external knowledge as flat chunks retrieved by embedding similarity, exposing a retrieval-as-lookup interface ill-suited to iterative reasoning agents. We propose LLM-Wiki, an agent-native retrieval system that operationalizes the Retrieval-as-Reasoning paradigm by treating external knowledge as a compilable, composable, and self-evolving structure rather than a static retrieval index. LLM-Wiki compiles documents into structured Wiki pages with bidirectional links, exposes search, read, and link-following operations through standard tool-calling interfaces, and introduces an Error Book for persistent structural and semantic self-correction. LLM-Wiki achieves state-of-the-art results on HotpotQA, MuSiQue, and 2WikiMultiHopQA, outperforming HippoRAG 2, LightRAG, and GraphRAG by 2.0-8.1 F1 points. On AuthTrace, LLM-Wiki achieves the best overall accuracy, with especially strong gains on multi-document structured queries, confirming that compilation-based retrieval generalizes beyond chain-style multi-hop reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。