研究库 论文知识库

内容库 / 论文

arXiv:2610.08452 · RAG 检索增强

Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents

Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents

类型：arxiv
标识：2610.08452
链接：http://arxiv.org/abs/2610.08452v1
主分类：rag
形态：method
TLDR：Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a pipeline is an expensive hyperparameter optimization problem over many interacting choices, from chunking and embedding model to reranking and generation. Existing optimizers, from greedy search to Bayesian optimization, reduce each trial to an aggregate score and search without modeling why a configuration performed as it did, even though the retrieved chunks already provide evidence about whether each failure occurred during retrieval or afte
副分类：agent
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-07-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 Tom 文献雷达 · Agent · RAG · 长上下文 · 2026-08-17 08:40 CST

笔记 Tom 文献雷达 · Agent RAG LongContext · 2026-09-04 08:40

笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-09-05 14:40

文档 Stephen 自测 · R60 · 2026-08-30

笔记 Tom 文献雷达 · Agent + RAG + Long-Context · 2026-07-18 14:40

笔记 Tom 文献雷达 · Agent + RAG + 长上下文 · 2026-08-27 20:40

arXiv

2610.08452

TLDR

Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a pipeline is an expensive hyperparameter optimization problem over many interacting choices, from chunking and embedding model to reranking and generation. Existing optimizers, from greedy search to Bayesian optimization, reduce each trial to an aggregate score and search without modeling why a configuration performed as it did, even though the retrieved chunks already provide evidence about whether each failure occurred during retrieval or afte

arXiv ↗ 中文全文