Iterative RAG

RAG: Retrieval-Augmented Generation

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Efficient Iterative Retrieval with Heterogeneous Batching
Sep 21, 2026Dohyun Park, Hubertus Franke, Daniel G. Waddington +2Retrieval-Augmented Generation LLM Serving
University of Illinois Urbana-Champaign · IBM Research
The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search
Aug 24, 2026Peiyang Liu, Xi Wang, Di Liang +1Iterative RAG Retrieval-Augmented Generation
National Engineering Research Center for Software Engineering, Peking University, China · Peking University, China · Tencent, China
Hybrid-IR: Dual-Path Hybrid Retrieval with Iterative Reasoning for Complex Medical Question Answering
Jun 24, 2026Sheng Wan, Jiahui Zhang, Zicheng Zhao +1Retrieval-Augmented Generation Iterative RAG
College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, China · School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
May 2, 2026Peiyang Liu, Ziqiang Cui, Xi Wang +2Retrieval-Augmented Generation Iterative RAG
National Engineering Research Center for Software Engineering, Peking University Beijing, China · City University of Hong Kong Hong Kong SAR, China · Tencent Technology Beijing, China
Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering
Apr 30, 2026Xupeng Chen, Binbin Shi, Chenqian Le +5Multimodal RAG Retrieval-Augmented Generation
New York University, New York, USA · Tsinghua University, Beijing, China · Independent Researcher +1
S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA
Apr 26, 2026Minghan Li, Junjie Zou, Xinxuan Lv +2Multi-Hop QA Retrieval-Augmented Generation
Soochow University, Suzhou, China
PAR $^2$ -RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
Mar 30, 2026Xingyu Li, Rongguang Wang, Yuying Wang +5Multi-Hop QA Retrieval-Augmented Generation
Oracle AI
Gradually Excavating External Knowledge for Implicit Complex Question Answering
Mar 9, 2026Chang Liu, Xiaoguang Li, Lifeng Shang +4Iterative RAG Question Answering
The University of Hong Kong · Huawei Noah’s Ark Lab
KGiRAG: An Iterative GraphRAG Approach for Responding Sensemaking Queries
Mar 2, 2026Isabela Iacob, Melisa Marian, Gheorghe Cosmin SilaghiIterative RAG Retrieval-Augmented Generation
Babes-Bolyai University, Business Informatics Research Center, Cluj-Napoca, Romania

Sep 21, 2026J/K move · Enter open · S save

Efficient Iterative Retrieval with Heterogeneous Batching

Dohyun Park, Hubertus Franke, Daniel G. Waddington, Swaminathan Sundararaman+1

University of Illinois Urbana-Champaign · IBM Research

Retrieval-Augmented Generation LLM Serving Iterative RAG LLM Inference Scheduling

Open paper AskPDF arXiv

Modern information retrieval increasingly employs both embedding and generative models to handle complex queries. However, current serving systems suffer from low throughput and poor GPU utilization because they execute these models in isolation. Coarse-grained partitioning, such as dedicating GPUs to specific tasks, fails to adapt to dynamic workloads and creates computational "bubbles". To address these, we present Orthrus, a serving system that performs heterogeneous batching within a unified inference loop. The primary challenge lies in unifying embedding and generation workloads with conflicting computational patterns while optimizing batch composition for high performance. Orthrus addresses these challenges through chunked embedding with incremental pooling and by adjusting batch composition in a workload-aware manner. Evaluation on four A100 GPUs shows that, relative to baseline deployments, Orthrus achieves 1.28

\times

--4.52

\times

higher throughput on controlled workloads and up to 55.8% lower end-to-end p99 latency on an iterative-RAG benchmark. We release our code at https://github.com/illinoisdata/Orthrus .