This page shows the most relevant public items for RAG, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Feb 5, 2026 • arXiv • Minghao Du, Yifan Sun, Zeyu Li
A-RAG proposes an agentic retrieval framework that exposes retrieval tools directly to large language models. Rather than treating retrieval as a static preprocessing step, the architecture allows ...
Paper • Feb 11, 2026 • arXiv • Pengcheng Zhou, Haochen Li, Zhiqiang Nie, JiaLe Chen, Qing Gong, Weizhen Zhang, Chun Yu
This paper introduces CogitoRAG, a cognitive-inspired retrieval-augmented generation framework designed to mimic human episodic memory and semantic gist formation. The system constructs a multi-dim...
Blog • Feb 17, 2026 • Towardsai • Florian June
Traditional Retrieval-Augmented Generation (RAG) is becoming a commodity; the next frontier is 'Cog-RAG.' This post details a new architecture where an agentic 'brain' evaluates a query, identifies...
Paper • Apr 11, 2025 • arXiv • Minh N. Nguyen, Sarah J. Conner, Wei Lin
Standard Retrieval-Augmented Generation (RAG) relies on static, single-pass semantic searches that often fail on complex, multi-hop queries. We introduce Agentic-RAG, an autonomous framework where ...
Paper • Dec 8, 2021 • arXiv • Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego de Las Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Maggiore, Chris Jones, Albin Cassirer, Andy Brock, Michela Paganini, Geoffrey Irving, Oriol Vinyals, Simon Osindero, Karen Simonyan, Jack W. Rae, Erich Elsen, Laurent Sifre
We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a 2 trillion token database, our R...
Paper • Feb 19, 2026 • arXiv • Florian June, Wei-Lin Chiang, Hao Peng
Traditional Retrieval-Augmented Generation (RAG) models employ a naive 'retrieve-then-read' pipeline, which frequently fails when addressing complex, multi-hop queries that require implicit reasoni...
Paper • Feb 7, 2026 • arXiv • Xingliang Hou, Yuyan Liu, Qi Sun, Haoxiu Wang, Hao Hu, Shaoyi Du, Zhiqiang Tian
IGMiRAG introduces a cognitive-inspired retrieval framework that simulates intuition-driven reasoning over hierarchical knowledge graphs. The system constructs a heterogeneous hypergraph to represe...
Paper • Jan 19, 2026 • arxiv.org • Chen et al.
Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper systematically reviews...
Paper • Feb 14, 2026 • arXiv • Rui Yu, Tianyi Wang, Ruixia Liu, Yinglong Wang
PT-RAG proposes a structure-aware retrieval framework designed specifically for long academic documents. Traditional RAG pipelines flatten documents into chunks, which destroys the natural hierarch...
Paper • Nov 20, 2025 • arXiv • Hao Hu, Yifan Feng, Ruoxue Li, Rundong Xue
Cog-RAG introduces a cognitive-inspired dual-hypergraph architecture designed to capture both thematic and entity-level relationships within large document collections. The framework constructs two...
Paper • Jul 28, 2025 • arXiv • Sarah Jenkins, Esq., Wei Chen, Marcus T. Holden
The legal discovery process involves manually cross-referencing millions of pages of depositions and emails to find logical contradictions. Standard search algorithms fail to connect multi-document...
It ranks public content for RAG using recent discussion, review, and engagement signals so you can triage faster. This guidance is specific to RAG topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use weekly for fast-moving updates, monthly for stable trend confirmation, and all-time for evergreen references. This guidance is specific to RAG topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use the linked entities section to jump to labs, companies, and experts connected to this topic and explore their timelines. This guidance is specific to RAG topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Yes. Use the follow button on this page to subscribe and track new high-signal activity. This guidance is specific to RAG topic page on Attendemia and is written so it still makes sense without reading other sections on the page.