Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ji, Yuelyu, Li, Zhuochun, Meng, Rui, He, Daqing
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915704229330944
author Ji, Yuelyu
Li, Zhuochun
Meng, Rui
He, Daqing
author_facet Ji, Yuelyu
Li, Zhuochun
Meng, Rui
He, Daqing
contents Multi-hop question answering (QA) requires systems to iteratively retrieve evidence and reason across multiple hops. While recent RAG and agentic methods report strong results, the underlying retrieval--reasoning \emph{process} is often left implicit, making procedural choices hard to compare across model families. This survey takes the execution procedure as the unit of analysis and introduces a four-axis framework covering (A) overall execution plan, (B) index structure, (C) next-step control (strategies and triggers), and (D) stop/continue criteria. Using this schema, we map representative multi-hop QA systems and synthesize reported ablations and tendencies on standard benchmarks (e.g., HotpotQA, 2WikiMultiHopQA, MuSiQue), highlighting recurring trade-offs among effectiveness, efficiency, and evidence faithfulness. We conclude with open challenges for retrieval--reasoning agents, including structure-aware planning, transferable control policies, and robust stopping under distribution shift.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00536
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
Ji, Yuelyu
Li, Zhuochun
Meng, Rui
He, Daqing
Computation and Language
Multi-hop question answering (QA) requires systems to iteratively retrieve evidence and reason across multiple hops. While recent RAG and agentic methods report strong results, the underlying retrieval--reasoning \emph{process} is often left implicit, making procedural choices hard to compare across model families. This survey takes the execution procedure as the unit of analysis and introduces a four-axis framework covering (A) overall execution plan, (B) index structure, (C) next-step control (strategies and triggers), and (D) stop/continue criteria. Using this schema, we map representative multi-hop QA systems and synthesize reported ablations and tendencies on standard benchmarks (e.g., HotpotQA, 2WikiMultiHopQA, MuSiQue), highlighting recurring trade-offs among effectiveness, efficiency, and evidence faithfulness. We conclude with open challenges for retrieval--reasoning agents, including structure-aware planning, transferable control policies, and robust stopping under distribution shift.
title Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
topic Computation and Language
url https://arxiv.org/abs/2601.00536