arXiv Computation and Language

Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting

arXiv Machine Learning

Jun 30

Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation

arXiv:2606. 29947v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes.

By Zhe Dong (University of Maine at Presque Isle), Fang Qin (Stanford University), Manish Shah (Independent Researcher), Yicheng Wang (Independent Researcher)

llms 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 AI

Jun 30

Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation

arXiv:2606. 29328v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding.

By Bingxue Zhang, Jianying Jia, Feida Zhu

rag multimodal benchmarks

arXiv AI

Aug 13

CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation

arXiv:2605. 04495v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance.

By Zhipeng Song, Yizhi Zhou, Xiangyu Kong, Jiulong Jiao, Xuezhou Ye, Chunqi Gao, Xueqing Shi, Yu Wang, Yuhang Zhou, Heng Qi

llms rag

arXiv Machine Learning

Jul 28

When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost

arXiv:2607. 24010v1 Announce Type: new Abstract: Active RAG systems decide when to retrieve external knowledge during generation, making them a budget-sensitive case of agentic RAG and self-adaptive retrieval.

By Pin Qian, Su Wang, Chong Peng, Junxian You, Lifei Liu, Haoran Yu, Yihang Chen, Xiaochong Jiang

rag agents

arXiv AI

Jul 3

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

arXiv:2604. 02091v2 Announce Type: replace-cross Abstract: Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation.

By Yuhang Wu, Xiangqing Shen, Fanfan Wang, Cangqi Zhou, Zhen Wu, Xinyu Dai, Rui Xia

llms rag reinforcement-learning benchmarks

arXiv Machine Learning

Jun 30

The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search

arXiv:2606. 28359v1 Announce Type: cross Abstract: Dense embedding retrieval compresses all relevance information into a single inner product, imposing a fundamental geometric limit -- the Voronoi Bottleneck -- on the number of query-document relevance patterns expressible at fixed embedding dimension (d).

By Charith Chandra Sai Balne, Rithwik Maramraju, Siddharth Pratap Singh, Rohit Upadhyay, Aditya Singh, Chittaranjan Tripathy, Yogananda Domlur Seetharama

rag

arXiv AI

Jun 9

sGPO: Trading Inference FLOPs for Training Efficiency in RLVR

arXiv:2606. 08854v1 Announce Type: cross Abstract: Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for the current policy.

By Shivchander Sudalairaj, Kai Xu, Akash Srivastava, Giorgio Giannone

reinforcement-learning

arXiv Machine Learning

Aug 3

QASP: Query-Adaptive Robust Vector Search Policy

arXiv:2607. 29606v1 Announce Type: cross Abstract: A fundamental challenge of vector search is achieving consistently high recall while minimizing computational costs.

By Hakan Ferhatosmanoglu, Kushal Kumar, Tal Wagner, Andy Warfield

rag

arXiv AI

Jun 30

CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval

arXiv:2606. 28365v1 Announce Type: cross Abstract: RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.

By Adnan Qidwai, Anand Eswaran, Sonam Mishra, Jaydeep Sen, Sachindra Joshi

rag agents safety

arXiv AI

Jul 28

LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory

arXiv:2607. 22690v1 Announce Type: new Abstract: Long-term memory lets LLM agents reuse past interactions, but raw dialogue histories are verbose and information-sparse.

By Jing Yu, Yibo Zhao, Jiaming Zhang, Xiang Li

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Aug 18

What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering

arXiv:2608. 14841v1 Announce Type: new Abstract: Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines.

By Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee, Carl Yang

llms nlp multimodal

Related stories