Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
This survey addresses the problem of opaque procedural choices in multi-hop QA for researchers, providing a structured comparison framework, but it is incremental as it synthesizes existing work rather than proposing new methods.
The paper tackles the lack of explicit analysis of retrieval-reasoning processes in multi-hop question answering by introducing a four-axis design framework to map and compare systems, synthesizing empirical trends from benchmarks like HotpotQA to highlight trade-offs in effectiveness, efficiency, and faithfulness.
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.