Medical question answering (QA) is a knowledge-intensive task demanding evidence-based reasoning across diverse sources. Despite the demonstrated efficacy of augmenting large language models (LLMs) with domain-specific knowledge graphs (KGs) for QA tasks, the prevailing single-KG paradigm neglects the benefits of multi-KG complementarity. This paper introduces KGFlow, a novel multi-KG reasoning paradigm that mitigates the incomplete coverage and fragmented evidence of single-KG approaches through three LLM agents. Given a query, Knowledge Explorer extracts relevant knowledge triples in parallel from heterogeneous sources. Graph Aligner then semantically harmonizes these triples into global reasoning paths, which are filtered by Contextual Pruner to preserve the most valuable paths for inference. Extensive experiments show that KGFlow achieves promising performance improvements compared to state-of-the-art techniques on five medical QA datasets. We further observe by cases that the plug-and-play nature of our framework enables its application to diverse KG combinations and multilingual scenarios, resulting in broader knowledge coverage than single-KG approaches.

Biomedical document-level relation extraction poses significant challenges beyond sentence-level tasks, as it necessitates the integration of evidence from entire documents and the ability for coherent cross-sentence reasoning. While pretrained language models (PLMs) demonstrate efficiency in handling local contexts, they often struggle with global dependency modeling. Conversely, large language models (LLMs) exhibit strong reasoning capabilities but tend to generate hallucinations in knowledge-intensive biomedical domains. This paper introduces CoRE, a novel cascade framework that leverages the complementary strengths of PLMs and LLMs through a detect-then-rethink paradigm. The PLM serves as an efficient detector for high-confidence relations, while challenging cases are forwarded to an LLM enhanced with semantic retrieval and iterative reasoning mechanisms. Experimental results on BioRED and CDR datasets show that CoRE achieves substantial improvements over state-of-the-art baselines, validating the effectiveness of the proposed cascade paradigm for complex biomedical relation extraction.