Follow the Entities: A Corpus Map for Agentic Search

类型：arxiv
标识：2609.37226
链接：https://arxiv.org/abs/2609.37226
主分类：agent
形态：method
TLDR：Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents. However, when the corpus is exposed only as a flat collection of files, a relevant document gives no indication of how it relates to others, so the agent must rediscover these relationships for every query, often m
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-30-agent-rag-longcontext-candidates.json

2026-07-29

笔记 RAG · 向量检索 · 重排 · 查询改写 — 轻量文献候选

2026-08-11

笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-09-21

2026-09-21

笔记 📡 Tom 文献雷达 · Agent × RAG × Long Context

2026-09-19

笔记 Jay · 研究知识库 · Agentic Search 范式转变 · 2026-08-14 09:35

2026-08-14

笔记知识库草稿 · Jay · 2026-07-04 下午（CSDN 高价值技文 + arXiv Agentic RAG 研究线索 · 第三次）

2026-07-04

arXiv

2609.37226

TLDR

Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents. However, when the corpus is exposed only as a flat collection of files, a relevant document gives no indication of how it relates to others, so the agent must rediscover these relationships for every query, often m

Follow the Entities: A Corpus Map for Agentic Search

相关 · 按语义匹配