Retrieval-Augmented Generation (RAG) has improved the factual grounding of large language models, but multi-hop question answering remains challenging because a system may retrieve semantically relevant yet evidence-incomplete contexts. Existing KG-guided RAG methods improve evidence coverage through graph expansion, but they often operate in a single-pass manner and lack an explicit mechanism for judging whether the assembled evidence is sufficient for reliable reasoning. Therefore, we propose AdaKG-RAG, an evidence-sufficiency-driven KG-guided RAG framework for multi-hop question answering. The core of AdaKG-RAG is a Hypothesis-and-Verification Retrieval (HVR) loop, which first forms a tentative answer from the current evidence, verifies whether the evidence is sufficient, and triggers targeted retrieval refinement when bridge facts are missing. To support this loop, AdaKG-RAG uses semantic-aware KG expansion and path-aware evidence organization to recover and structure candidate bridge evidence, followed by answer-aware supporting-fact (SF) reranking for better answer–evidence alignment. Experiments on HotpotQA and MuSiQue, together with a long-context evaluation on TriviaQA, show that AdaKG-RAG improves both answer quality and evidence retrieval quality over representative RAG and KG-RAG baselines. Further analysis indicates that HVR contributes the largest performance gain, while graph-based modules provide complementary improvements in evidence coverage and organization.
Yuan et al. (Sat,) studied this question.