一作ACL 2026Workshop· Natural Language Processing
Test-Time Strategies for More Efficient and Accurate Agentic RAG
Abhinav Sharma · Brian Zhang · Deepti Guntur · Zhiyang Zuo · Shreyas Chaudhari · Wenlong Zhao · Franck Dernoncourt · Puneet Mathur · Ryan A. Rossi · Nedim Lipka
摘要
Retrieval-Augmented Generation (RAG) systems face challenges with complex, multi-hop questions, and iterative agentic frameworks such as Search-R1 (Jin et al., 2025) have been proposed to address these complexities. However, such approaches can introduce inefficiencies, including repetitive retri...