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.
arXiv:2606. 28361v1 Announce Type: cross Abstract: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative retrieval-reasoning rounds deliver strong multi-hop accuracy.
By Kuan Yan, Zhiqing Tang, Tian Wang, Weijia Jia
arXiv:2608. 13076v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success in natural language understanding and generation, but their deployment is constrained by high computational demands.
By Divya Jyoti Bajpai, Kishan Kumar Upadhyay, Manjesh Kumar Hanawal
arXiv:2608. 15919v1 Announce Type: cross Abstract: Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-specific corpora.
By Nicola Cogotti
arXiv:2606. 00426v1 Announce Type: new Abstract: Federated continual learning (FCL) lets distributed clients adapt language-model heads to evolving NLP tasks without sharing raw text.
By Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj Sharma
arXiv:2604. 19047v2 Announce Type: replace-cross Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity.
By Hanjun Cho, Jay-Yoon Lee
arXiv:2608. 03048v1 Announce Type: cross Abstract: Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: sequential chunk-wise updates can overwrite early critical evidence with later irrelevant content, and serial inter-chunk dependencies limit parallelism and cause latency to increase with context length.
By Dawei Liu, Haixu Song, Shuang Cheng, Shijie Wang, Haozheng Hou, Kaifeng Liu, Ermo Hua, Zhonghang Yuan, Zhijie Zhong, Yuchen Fan, Biqing Qi, Bowen Zhou
arXiv:2502. 11007v5 Announce Type: replace Abstract: Compared to traditional machine learning models, recent large language models (LLMs) can exhibit multi-task-solving capabilities through multi-modal data sources and multi-turn conversations.
By Liangqi Yuan, Dong-Jun Han, Shiqiang Wang, Christopher G. Brinton
arXiv:2606. 04581v1 Announce Type: cross Abstract: Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs).
By Haotian Zheng, Zhanwei Wang, Mingyao Cui, Chang Cai, Hongyang Du, Kaibin Huang
arXiv:2608. 02560v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) imposes a prefill cost proportional to retrieved context length, and -- with Transformer backbones -- a KV-cache that grows with each generated token.
By Anusha Madan Gopal, Aras Pirbadian, Kristofor D. Carlson, M Anthony Lewis, Jonathan Tapson
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)
Large language models increasingly rely on external tools to access up-to-date information, perform computation, and interact with the outside world. For autoregressive models, tool use naturally fits the generation process: the model emits a tool call, waits for the result, and then continues generating.