arXiv Machine Learning September 14, 2026 By Qiaomu Li, Qiuyuan Zhang, Nong Ming

Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing?

Read the original on arXiv Machine Learning →

The paper investigates whether retrieval-time signals add value to Adaptive Retrieval-Augmented Generation (RAG) routing when the query is already known. Experiments across document, audio, and video RAG compare routers that use only the query versus those that also incorporate retrieval signals, keeping all other factors constant. The results show that adding retrieval signals does not reliably improve routing decisions over a query-only baseline, suggesting that any routing benefit must be explicitly demonstrated rather than presumed.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 12

Rethinking RAG in Long Videos: What to Retrieve and How to Use It?

arXiv:2606. 13141v1 Announce Type: new Abstract: Retrieval-augmented generation is moving beyond text into long, egocentric video, where systems must select query-relevant chunks across multiple modalities and temporal granularities.

By Yuho Lee, Jisu Shin, Nicole Hee-Yeon Kim, Jihwan Bang, Juntae Lee, Kyuwoong Hwang, Fatih Porikli, Hwanjun Song

rag benchmarks

arXiv AI

Jun 3

Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs

arXiv:2606. 02581v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and end-to-end latency.

By Sanjay Mishra

llms rag benchmarks safety

arXiv Machine Learning

Aug 11

SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems

arXiv:2608. 08237v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems in production operate under strict service level objectives (SLOs) on tail latency and infrastructure cost.

By Muhammad Faizan Raza (Luna), Shuo (Luna), Yang, Satish Mahadevan Srinivasan

llms rag

arXiv AI

Jun 2

RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering

arXiv:2606. 02488v1 Announce Type: new Abstract: Multi-hop question-answering systems often use expensive retrieval on every question.

By Yuyang Li, Zihe Yan, Tobias K\"afer

llms rag nlp benchmarks

arXiv Computer Vision

Aug 24

Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding

arXiv:2608.20805v1 Announce Type: new Abstract: Long-form video understanding remains challenging for video agents due to the mismatch between query demands and evidence acquisition strategies. Altho...

By Tianyue Wang, Xuying Wu, Yuxiang Ma, Ruiming Liang, Jiaxuan Kang, Yanchao Hao, Zheng Wei, Leigang Qu, Haiyun Guo, Jinqiao Wang

rag agents benchmarks

arXiv Computer Vision

Oct 9

Autoregressive Retriever: Improving Query Understanding from Item Feedback for Universal Multimodal Retrieval

The paper introduces the AutoRegressive Retriever (ARR), a multimodal retrieval model that iteratively refines a query embedding by selecting informative items and incorporating their content. ARR alternates between retrieval and query update, using stepwise contrastive supervision and reinforcement learning to optimize item selection and final ranking. Experiments show ARR outperforms baselines on in‑domain and zero‑shot benchmarks, with feedback improving both inference performance and initial query embeddings.

By Jianfei Zhao, Yifan Wang, Feng Zhang, Xin Sun, Chong Feng, Zhixing Tan, Yang Luo, Boyuan Pan, Xu Kai, Yao Hu

rag reinforcement-learning fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

Rethinking RAG in Long Videos: What to Retrieve and How to Use It?

Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs

SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems

RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering

Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding

Autoregressive Retriever: Improving Query Understanding from Item Feedback for Universal Multimodal Retrieval