@inproceedings{10.1007/978-981-92-2584-2_37,
	title        = {{URAG 2.0: An Agentic Dual Retrieval Framework for Enhanced Reasoning in RAG-Based QA Systems}},
	author       = {Nguyen, Long S. T. and Vo, Quynh T. N. and Nguyen, Thi T. and Quan, Tho T.},
	year         = 2027,
	booktitle    = {Information and Communication Technology},
	publisher    = {Springer Nature Singapore},
	address      = {Singapore},
	pages        = {469--481},
	isbn         = {978-981-92-2584-2},
	editor       = {Buntine, Wray and Fjeld, Morten and Sch{\"o}ffmann, Klaus and Tran The, Truyen and Tran, Minh-Triet and Binh, Huynh Thi Thanh and Dam, Tuan},
	abstract     = {Large Language Models (LLMs) have advanced Question-Answering (QA) systems but still suffer from factual errors and limited reasoning when relying solely on implicit knowledge. Retrieval-Augmented Generation (RAG) mitigates these issues by grounding responses in external corpora, yet existing pipelines often depend on a single retrieval channel, which hampers multi-hop reasoning and underutilizes heterogeneous evidence. Graph-based extensions attempt to capture structural relations but remain costly, noisy, and ultimately constrained to one stream. To address these limitations, we propose URAG 2.0, an agentic dual-retrieval framework that extends our original URAG design. URAG 2.0 constructs two complementary indices: Frequently Asked Questions (FAQs) distilled and paraphrastically enriched from documents, and semantically chunked documents refined with context-aware rewriting. At inference, both indices are queried in parallel, and an orchestration layer fuses and ranks evidence before synthesis. Experiments across multiple QA benchmarks demonstrate that URAG 2.0 consistently outperforms advanced RAG baselines in both factual QA and multi-hop reasoning, establishing dual retrieval as a promising direction for building more accurate and explainable QA systems.}
}