Large language models face challenges with hallucinations and outdated knowledge in biomedical applications, prompting the development of improved retrieval-augmented generation methods. Existing approaches often struggle with fragmented medical knowledge due to reliance on single retrieval paths and static strategies that hinder deep reasoning. To address these limitations, researchers introduced Hybrid-IR, a dual-path framework featuring an iterative retrieve-reason mechanism for complex medical question answering. This system integrates graph-based retrieval to explore structured knowledge alongside dense retrieval for fine-grained semantic matching. The model progressively refines its reasoning trajectory through an iterative loop between retrieval and reasoning steps. Experiments conducted on three widely used medical QA benchmarks demonstrate the effectiveness of this proposed approach.