PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nahid, Md Mahadi Hasan, Rafiei, Davood
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915557383602176
author Nahid, Md Mahadi Hasan
Rafiei, Davood
author_facet Nahid, Md Mahadi Hasan
Rafiei, Davood
contents Retrieval plays a central role in multi-hop question answering (QA), where answering complex questions requires gathering multiple pieces of evidence. We introduce an Agentic Retrieval System that leverages large language models (LLMs) in a structured loop to retrieve relevant evidence with high precision and recall. Our framework consists of three specialized agents: a Question Analyzer that decomposes a multi-hop question into sub-questions, a Selector that identifies the most relevant context for each sub-question (focusing on precision), and an Adder that brings in any missing evidence (focusing on recall). The iterative interaction between Selector and Adder yields a compact yet comprehensive set of supporting passages. In particular, it achieves higher retrieval accuracy while filtering out distracting content, enabling downstream QA models to surpass full-context answer accuracy while relying on significantly less irrelevant information. Experiments on four multi-hop QA benchmarks -- HotpotQA, 2WikiMultiHopQA, MuSiQue, and MultiHopRAG -- demonstrates that our approach consistently outperforms strong baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14278
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
Nahid, Md Mahadi Hasan
Rafiei, Davood
Computation and Language
Artificial Intelligence
Information Retrieval
Retrieval plays a central role in multi-hop question answering (QA), where answering complex questions requires gathering multiple pieces of evidence. We introduce an Agentic Retrieval System that leverages large language models (LLMs) in a structured loop to retrieve relevant evidence with high precision and recall. Our framework consists of three specialized agents: a Question Analyzer that decomposes a multi-hop question into sub-questions, a Selector that identifies the most relevant context for each sub-question (focusing on precision), and an Adder that brings in any missing evidence (focusing on recall). The iterative interaction between Selector and Adder yields a compact yet comprehensive set of supporting passages. In particular, it achieves higher retrieval accuracy while filtering out distracting content, enabling downstream QA models to surpass full-context answer accuracy while relying on significantly less irrelevant information. Experiments on four multi-hop QA benchmarks -- HotpotQA, 2WikiMultiHopQA, MuSiQue, and MultiHopRAG -- demonstrates that our approach consistently outperforms strong baselines.
title PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2510.14278