Hugging Face Trending Papers July 21, 2026

RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency

Read the original on Hugging Face Trending Papers →

Public institutions hold large volumes of sensitive documents and support tickets that cannot leave the premises, ruling out cloud-hosted language models entirely. We report on RAGAL, a retrieval-augmented assistant for the technical-support team of AFIR, the Romanian Agency for Financing Rural Investments, built and operated under three hard constraints: zero data egress (no external API calls, even for synthetic data), a read-only mandate (the assistant drafts, humans execute), and a single 8 GB consumer laptop as the only development and training machine.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 30

Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval

arXiv:2606. 30473v1 Announce Type: cross Abstract: We study retrieval over catalogs of structured metadata, where each record is a small schema whose fields answer different kinds of query.

By Aivin V. Solatorio, Olivier Dupriez, Rafael Macalaba

llms rag agents fine-tuning benchmarks

arXiv AI

Jun 9

SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance

arXiv:2606. 09441v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) injects LLM queries with relevant documents to improve response quality.

By Rya Sanovar, Srikant Bharadwaj, Hritvik Taneja, Moinuddin Qureshi

llms rag

arXiv AI

Jun 16

CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation

arXiv:2606. 15179v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) has emerged as a pivotal technique for improving language models by incorporating external knowledge at inference time.

By Xuedong Hu, Zhiqing Tang, Zhi Yao, Tian Wang, Weijia Jia

llms rag efficiency safety

arXiv AI

Jun 12

ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs

arXiv:2606. 12451v1 Announce Type: new Abstract: Large language models deployed as agents over large tool catalogs face a critical tool-retrieval bottleneck.

By Ashutosh Hathidara, Sai Shruthi Sistla, Sebastian Schreiber, Sahil Bansal

llms rag agents fine-tuning 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

Jul 29

Sheet As Token: A Graph-Enhanced Representation for Multi-Sheet Spreadsheet Understanding

arXiv:2605. 05811v2 Announce Type: replace Abstract: Workbook-scale spreadsheet understanding is increasingly important for language-model-based data analysis agents, but remains challenging because relevant information is often distributed across multiple sheets with heterogeneous schemas, layouts, and implicit relationships.

By Yiming Lei, Yuhang Yao, Yujia Zhang, Yiqi Wang, Bo Guan, Depei Zhu, Chunhui Wang, Zhuonan Hao, Tianyu Shi

rag agents

Related stories

Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval

SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance

CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation

ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs

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

Sheet As Token: A Graph-Enhanced Representation for Multi-Sheet Spreadsheet Understanding