Retrieval-augmented generation

Evidence in the last complete seven days

Source mentions

7

Previous seven days 9

Distinct sources

2

Previous 3

Comparable growth

Not comparable

Ranking appearances

0

Collection observations and undated records are separate from dated publication counts. Observed in 7d：4 · Undated records：2

Daily history · up to 90 days

Bars show dated source mentions. The latest UTC day may be incomplete. Zero mentions and missing collection coverage are different conditions.

Dotted markers indicate days with no record. They are not counted as zero mentions.

Source evidence

Sources in the evidence shown：arXiv 17 · V2EX 4 · Hacker News 3 · GitHub Trending 2

1. arXiv · Published Nov 5, 2026

   RAGCompass: Generalizable Retriever Routing via Reranking

   arXiv:2611.05596v1 Announce Type: new Abstract: Different retrievers exist for retrieval-augmented generation, yet none performs best for all queries. Therefore, the key question is: given a query and retrieved passages from different retrievers, which one is most suited for that query? Existing routers usually make predictions from query-specific features a

   View source record →

2. arXiv · Published Nov 4, 2026

   From Logs to Faults: Reference-Free Fault Localization for Retrieval-Augmented Generation Pipelines

   arXiv:2611.03725v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) pipelines are widely used for domain-specific question answering, yet locating faults remains manual and time-consuming. Fault localization is challenging because RAG pipelines consist of interdependent stages, where faults can propagate downstream, masking their origin, or

   View source record →

3. arXiv · Published Nov 2, 2026

   Better Retrievers, Worse Labels: How Incomplete Relevance Judgments Distort Abstention Evaluation in Conversational RAG

   arXiv:2610.40966v1 Announce Type: new Abstract: Conversational RAG benchmarks such as MTRAG and RETECO evaluate retrieval and generation end to end: each system answers from its own retrieval, so abstention must be scored against whether each retrieved context is sufficient. A convenient shortcut reads sufficiency off the relevance judgments and treats a con

   View source record →

4. arXiv · Published Nov 2, 2026

   Language Models Show Conformity Bias in RAG: When the Majority Endorses a Poisoned Claim

   arXiv:2610.41012v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can expose language models to misleading evidence in retrieved documents. We investigate whether increasing the number of mutually agreeing poisoned documents affects a model's ability to detect misinformation. We evaluate 200 randomly selected questions from SciFact (random

   View source record →

5. V2EX · Published Oct 31, 2026

   [程序员] 我在 2 核 2G 云主机上跑 OpenViking：一次关于云主机、模型选型与长期成本的真实复盘

   最近把自己的 AI Coding Agent 记忆底座迁移到了自建的 OpenViking 上（ OpenViking 真的满足我所有的要求：即是各种 Agent 的统一大脑自进化、又是知识库，检索的时候是两方面综合起来的）。RAG 相关的东西看着挺吓人，动辄推荐高配服务器和本地显存，实际上用下来，只要选型想清楚，一台几十块钱的入门级云服务器完全能跑得飞起。 这篇不是教你怎么敲命令的安装教程，只是聊聊折腾这一圈下来，在云主机、模型组合、算力开销上的一些真实心得和踩坑取舍。 1. 云主机：为什么我选 99 元的 2G ，不选友商更便宜的 4G ？ 买云服务器时，第一眼很容易被一些友商“几十块钱买 4G 甚至 8G”的新客促销吸引。但我最终还是选了阿里云 99 元/年的 2 核 2G （ ecs.e-c1m1.la

   View source record →

6. V2EX · Published Oct 29, 2026

   [分享创造] 我把斯坦福 CS329Z 的 Agent 学习资料整理成了中文教程，做了个打开就能学的阅读网站。

   我把斯坦福 CS329Z 的学习资料整理成了中文教程，做了个打开就能学的阅读网站。非常适合会一点 Python 、调过模型 API ，想继续学 Agent 的朋友。 19 章覆盖 RAG 、工具调用、上下文、记忆、多 Agent 、评测和安全，附 4 项实践材料和配套代码导读。既可以按章节学习，也方便结合代码理解这些模块怎么配合。 学概念、看代码、做项目时查资料，都方便。网站有目录、全文搜索和深浅主题，GitHub 还提供 Markdown 和单文件 HTML ，下载后就能离线学。 在线： https://cs329z-course-review-20261029.wanghao162263.chatgpt.site GitHub： https://github.com/wanghao-SunSky/cs329

   View source record →

7. arXiv · Published Oct 29, 2026

   OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning

   arXiv:2610.36335v1 Announce Type: new Abstract: Large language models (LLMs) perform well across many real-world tasks but remain prone to hallucination, limiting their reliability in domains such as biomedicine and healthcare, where answers must be grounded in established knowledge. Retrieval-augmented generation (RAG) mitigates this problem by incorporatin

   View source record →

8. arXiv · Published Oct 29, 2026

   RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG

   arXiv:2610.36444v1 Announce Type: new Abstract: Web-based applications increasingly rely on understanding long multimodal documents, where answering questions often requires combining information across pages, tables, and figures. Agentic retrieval-augmented generation addresses these tasks through iterative retrieval and reasoning. However, Agentic executio

   View source record →

9. V2EX · Published Oct 28, 2026

   [分享创造] [开源] 整理了一份 AI Agent 学习与面试手册， 22 章课程、92 道详解题

   工具调用超时，后端可能已经创建了工单。这时如果换个操作 ID 再提交一次，一份申请就可能变成两份。 学 Agent 时，我希望这类执行过程能讲清楚。术语记住了，出问题以后还得知道查哪里，总不能让模型一句“已完成”替后端签收。 于是把学习资料、面试题和实验整理成了一个中文仓库，方便自己复习，也分享给正在学习 AI Agent ／大模型应用开发的朋友： GitHub： https://github.com/harrytted/ai-agent-interview-playbook 目前主要有这些内容： 10 章基础课程：从模型与上下文，讲到工具循环、RAG 、记忆、评测和可靠性。 12 章进阶课程：继续讨论长任务执行、崩溃恢复、工具路由、多 Agent 、性能、安全与训练。 92 道详解题：每题包含口述短答、详细答

   View source record →

10. arXiv · Published Oct 27, 2026

    Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers

    arXiv:2610.32110v1 Announce Type: new Abstract: Agents and verifiers often rely on the text a tool prints, and that text can misrepresent what the tool actually did, even when the tool's computation is correct. We saw this happen in a production RAG research system used by the Pilsudski Institute in New York, where tool output formatters misled an agent into

    View source record →

11. arXiv · Published Oct 27, 2026

    Multi-Agent Retrieval-Augmented Causality Assessment (MARCA) of Individual Case Safety Reports in Pharmacovigilance

    arXiv:2610.33279v1 Announce Type: new Abstract: Introduction: Increasing volumes of individual case safety reports (ICSRs) challenge expert-led causality assessment in pharmacovigilance. We developed MARCA (Multi-Agent Retrieval-Augmented Causality Assessment), a four-agent framework for Naranjo-based assessment, and evaluated agreement with human experts an

    View source record →

12. Hacker News · Published Oct 27, 2026

    Show HN: Limma – MCP for total recall and precision in data retrieval for agents

    Hello, my name is Berend Graham. My cofounder Shiv Oberai and I have been working on Limma for a year now with the goal of building a proactive solution to the reliability issues that plague practical AI and agentic use in companies with RAG. Limma is a single MCP that exists for the sole purpose of ensuring that the right information is retrieved with every

    View source record →

13. arXiv · Published Oct 24, 2026

    Compiling Autoregressive LLM Control into Policy-Exact Parallel Inference for Hierarchical RAG

    arXiv:2610.30664v1 Announce Type: new Abstract: Large language models increasingly act as controllers in structured decision pipelines, yet their decisions are still executed by autoregressive text decoding. Hierarchical RAG is one such setting: at each frontier of a document tree, an LLM commits to $b$ of $k$ sections under an input-dependent action grammar

    View source record →

14. arXiv · Published Oct 24, 2026

    ULME: Predictive Coupling for Mutually Reinforcing Embedding and Language Modeling

    arXiv:2610.30705v1 Announce Type: new Abstract: Text embedding and text generation are two of the most useful capabilities of modern large language models, yet they are typically provided by separate specialized models (an embedder and a generator) trained with incompatible objectives and deployed side by side in retrieval-augmented generation and agent syst

    View source record →

15. arXiv · Published Oct 22, 2026

    A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation

    arXiv:2610.28686v1 Announce Type: new Abstract: Query clarification is essential for retrieval-augmented generation (RAG) systems that face ambiguous user queries. We consider multi-turn grounded conversational scenarios where a user query is either ill-formed or ambiguous in the context of the prior dialog or, more interestingly, it may be well-formed but w

    View source record →

16. arXiv · Published Oct 22, 2026

    Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG

    arXiv:2610.28957v1 Announce Type: new Abstract: Scanning every passage in a long document seems thorough, but does it preserve more useful evidence or produce better answers? We compare 11 retrieval configurations spanning lexical and dense search, hybrid reranking, and full-document scanning with Jev, OpenAI Decisions, and Cloudflare Clef. Our evaluation us

    View source record →

17. arXiv · Published Oct 22, 2026

    C$^2$U in RAG: Compositional Concept Unlearning in Retrieval-Augmented Generation

    arXiv:2610.29223v1 Announce Type: new Abstract: Retrieval-augmented generation can expose unwanted concepts through retrieved evidence even when the generator is moderated. We study query-side concept suppression with a fixed encoder and document index. Compositional Concept Unlearning (C$^2$U) routes a profile-derived direction through an augmented atom ban

    View source record →

18. arXiv · Published Oct 21, 2026

    The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering

    arXiv:2610.26951v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is the dominant paradigm for grounding large language models in external corpora, but its similarity-driven, chunked pipeline has structural blind spots: it cannot anticipate which passages a question requires and discards document-level context that resolves cross-passage r

    View source record →

19. GitHub Trending · Published Not supplied

    headroomlabs-ai/headroom

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    View source record →

20. GitHub Trending · Published Not supplied

    ruvnet/ruflo

    🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and nativ

    View source record →

21. arXiv · Published Oct 19, 2026

    When Does Uncertainty Measure RAG Hallucination Risk?

    View source record →

22. arXiv · Published Oct 19, 2026

    Evidence-Gated Bilingual RAG for Reliable Consumer Banking Search

    View source record →

23. V2EX · Published Oct 10, 2026

    [开源软件] 折腾了一个 Go Agent：魔改 Runtime + Hybrid RAG + llama.cpp + WebGPU，分享一下实现

    View source record →

24. arXiv · Published Oct 9, 2026

    RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation

    View source record →

25. Hacker News · Published Oct 7, 2026

    We Built an Alternative to Vector RAG for AI Agent Memory

    View source record →

26. Hacker News · Published Oct 5, 2026

    Show HN: Halo – A Personal AI with On-Device Harness, Memory and Browser Agent

    Halo is privacy focused personal assistant for iOS that uses a custom built agent harness with support to use you existing LLM subscriptions, Wiki based memory system backed by on-device RAG, a full-fledged local browser agent, chat with generative UI and more. TLDR: It's a better version of Hermes/OpenClaw for iOS, without needing a server! The better part

    View source record →

Review priority 64 / 100

This score orders research candidates. It is not search volume, a forecast or verified commercial demand.

• Evidence

  24 / 30

  Distinct dated articles or first observations; repeat crawling adds nothing.

• Publisher diversity

  16 / 25

  Conservative owner grouping; syndicated copies count once.

• Comparable change

  0 / 20

  Comparable complete weeks only; no percentage from a zero baseline.

• Recent evidence

  14.5 / 15

  Latest publication or first observation, not repeated fetch time.

• Name specificity

  9.7 / 10

  Explicit entities and technical concepts outrank ambiguous acronyms.

Limitations and interpretation

• First observation is a collection milestone, not proof that a word or product is new to the world.
• Counts describe monitored public sources, not the whole web or search demand.
• First observed here is not the invention date of a name or idea.
• Candidates come from public titles, summaries and entity URLs, not verified full-text analysis.
• Owner grouping is conservative; undisclosed syndication may remain.
• Undated observations cannot establish publication growth.
• An established concept or common product name retained as a baseline, not a newly invented term.
• Both weeks need adequate, comparable collection coverage.
• Sources behind this term changed or lack a comparable baseline.