https://ym-xu.github.io/living-survey/fields/rag/#tag=retrieverEmbedding models, rerankers, chunking and the index itself.Thu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2611.11010https://arxiv.org/abs/2611.11010Sat, 07 Nov 2026 00:00:00 +0000Uday Allu Graph-based retrieval-augmented generation (GraphRAG) improves multi-hop question answering, but deployed systems face two costs that research comparisons rarely measure: building the graph, and removing documents from it. We present Lightfoot, a GraphRAG system in which every entity, link, fact and synonym edge is a d…https://arxiv.org/abs/2611.10405https://arxiv.org/abs/2611.10405Sat, 07 Nov 2026 00:00:00 +0000Hongyuan Xu, Dezhi Ye, Jiahao Cao, Jie Liu, et al. High-precision text reranking is a critical component in modern search, recommendation, and agentic retrieval-augmented generation (RAG) systems. We present Yuanbao-Reranker, a family of general-purpose dense rerankers spanning 0.6B, 4B, and 8B parameter scales built upon the Qwen3 backbone. To construct diverse and re…https://arxiv.org/abs/2611.06498https://arxiv.org/abs/2611.06498Wed, 04 Nov 2026 00:00:00 +0000Georgios Feretzakis, Alexandros Papaspyridis Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors. A signature proves who published a pack, not that its vectors encode its text. We study this text-vector integrity gap. A verifier that recomputes vectors and accepts…https://arxiv.org/abs/2611.06481https://arxiv.org/abs/2611.06481Wed, 04 Nov 2026 00:00:00 +0000Jyotin Goel, Abhinav Arun, Tejas Prakash Agarwal, Bhaskarjit Sarmah, et al. Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus. Yet retrieval strategies are designed around the structure their own construction pipeline produces, and whether they survive a change of construction is rarely tested. We study this cross-c…https://arxiv.org/abs/2611.04625https://arxiv.org/abs/2611.04625Tue, 03 Nov 2026 00:00:00 +0000Manzong Huang, Chenyang Bu, Yi He, Jiapu Wang, et al. Multi-hop retrieval-augmented generation (RAG) supports Web information seeking and fact verification by recovering complementary evidence across related pages within a limited retrieval budget. Scoring evidence independently against the original question can miss supporting units whose relevance emerges through interm…https://arxiv.org/abs/2611.04264https://arxiv.org/abs/2611.04264Tue, 03 Nov 2026 00:00:00 +0000Janet Sung, Kainan Zhou, Gangzhen Qian, Hang Xiao, et al. External text can affect a retrieval-augmented generation (RAG) system only after the retriever admits it to the model context. We stress this admission step while varying document content, attacker query information, per-target poison budget, and contamination scope. Across 623 Benchmarking Information Retrieval (BEIR…https://arxiv.org/abs/2611.02387https://arxiv.org/abs/2611.02387Mon, 02 Nov 2026 00:00:00 +0000Yibo Wang, Jisheng Dang, Bimei Wang, Jiongpei Hou, et al. Retrieval-augmented generation (RAG) extends large language models with external evidence, yet relevant evidence does not ensure that a generator can use it. Indiscriminate retrieval can degrade task performance while adding retrieval and long-context inference costs. Existing methods neither determine before large-sca…https://arxiv.org/abs/2610.41335https://arxiv.org/abs/2610.41335Fri, 30 Oct 2026 00:00:00 +0000Ziniu Liu, Xiaoyang Chen, Dezhi Ye, Jie Liu, et al. Retrieval-augmented generation (RAG) over visually rich documents must find both relevant content and the evidence that supports an answer. Screenshot retrieval preserves images and page structure, but written facts within screenshots also need to be searchable. Moreover, topical relevance alone does not identify which…https://arxiv.org/abs/2610.40966https://arxiv.org/abs/2610.40966Thu, 29 Oct 2026 00:00:00 +0000Ivan Kochergin, Vasily Konovalov 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 context wit…https://arxiv.org/abs/2610.40409https://arxiv.org/abs/2610.40409Thu, 29 Oct 2026 00:00:00 +0000Chenjie Qiu, Zixuan Zeng, Shaobin Shi, Bingfeng Chen, et al. Complex questions in retrieval-augmented generation require evidence spread over several documents, and an answer is reliable only when the retriever finds all of it. Chain embedding retrievers collect such evidence step by step, re-encoding the question together with the passages retrieved so far, and we find that the…https://arxiv.org/abs/2610.37358https://arxiv.org/abs/2610.37358Tue, 27 Oct 2026 00:00:00 +0000Zhouting Zhao Retrieval-augmented generation (RAG) can benefit from more sophisticated retrieval, but extra retrieval may be unnecessary for many questions and gains in evidence retrieval may not translate into faithful or correct answers. We study a cost-aware, two-action retrieval policy that chooses between a dense-retrieval-plus…https://arxiv.org/abs/2610.37080https://arxiv.org/abs/2610.37080Tue, 27 Oct 2026 00:00:00 +0000Peichun Hua, He Sun, Zirui Zhuang, Qi Qi, et al. Web retrieval-augmented generation (RAG) splits a page into fixed-size text chunks or, in recent visual pipelines, screenshot tiles, and the retrieved item serves at once as the unit of indexing, ranking, and reading. We trace answer evidence from source HTML to reader input over the full English Wikipedia and find tha…https://arxiv.org/abs/2610.36991https://arxiv.org/abs/2610.36991Tue, 27 Oct 2026 00:00:00 +0000Zafer Sahinoglu, Abdulazeez Mohammed, Buse Yaren Kazangirler, Cahit Berkay Kazangirler Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved context. Although dense retrieval is effective for local semantic matching, independently ranked retrieval can return redundant passages, miss cross-chunk depende…https://arxiv.org/abs/2610.36557https://arxiv.org/abs/2610.36557Tue, 27 Oct 2026 00:00:00 +0000Yifan Zhao, Qianyang Zhao, Xinyu Guan, kai wei, et al. Chunking is a fundamental preprocessing step in retrieval-augmented generation (RAG), yet most existing chunkers rely primarily on heuristics. We introduce the Question--Evidence-Supervised Chunker (QESChunker), to our knowledge the first method for constructing static chunk indices from question--evidence supervision.…https://arxiv.org/abs/2610.36444https://arxiv.org/abs/2610.36444Tue, 27 Oct 2026 00:00:00 +0000Zekai Chen, Hao Zhu, Yu Liu, Xunkai Li, et al. 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 execution is not…https://arxiv.org/abs/2610.34866https://arxiv.org/abs/2610.34866Mon, 26 Oct 2026 00:00:00 +0000Zicheng Zhao, Linhao Luo, Zongji Yu, Junnan Dong, et al. Large Language Models (LLMs) have shown remarkable capabilities across tasks, but they still struggle with complex reasoning that requires integrating scattered knowledge. Graph Retrieval-Augmented Generation (GraphRAG) addresses this challenge by organizing fragment knowledge as graphs, while recent Graph Foundation M…https://arxiv.org/abs/2610.34816https://arxiv.org/abs/2610.34816Mon, 26 Oct 2026 00:00:00 +0000Qiaomu Li, Ying Xie Retrieval-augmented generation (RAG) systems often use a dedicated reranker to choose which retrieved candidates reach the language model. Reranking improves relevance but adds latency, so teams look for faster alternatives. System-1style decision models make direct, structured predictions instead of generating long re…https://arxiv.org/abs/2610.34683https://arxiv.org/abs/2610.34683Mon, 26 Oct 2026 00:00:00 +0000Jaeyoung Park, Hantian Zhang, Kexin Rong, Steven Euijong Whang Group fairness in retrieval-augmented generation (RAG) systems is typically evaluated using metrics aggregated across queries. However, such metrics can conceal topic-level disparities: a system may favor women on questions about human rights and men on questions about actors and filmmakers, appearing nearly neutral ov…https://arxiv.org/abs/2610.37697https://arxiv.org/abs/2610.37697Sat, 24 Oct 2026 00:00:00 +0000Joe Egan, Ben Elliot, Samuel Van Stroud, Alex Sopio, et al. Large scientific collaborations produce extensive internal documentation spread across heterogeneous systems, making it difficult for collaborators to locate and reuse existing knowledge. We present chATLAS, a deployed Retrieval-Augmented Generation (RAG) assistant developed for the ATLAS experiment at CERN. The system…https://arxiv.org/abs/2610.33511https://arxiv.org/abs/2610.33511Sat, 24 Oct 2026 00:00:00 +0000Kaifeng Jin, Yuchen Yan, Zhichen Zeng, Xiao Lin, et al. Textual graph question answering (GraphQA) and graph-based retrieval-augmented generation (GraphRAG) have gained increasing attention as a way to ground large language models (LLMs) on structured knowledge. Despite extensive efforts, existing methods still face two key gaps. The first is an architectural gap: existing …https://arxiv.org/abs/2610.31606https://arxiv.org/abs/2610.31606Thu, 22 Oct 2026 00:00:00 +0000Miguel Mochizuki Silva, Samuel Ismael, Mateus C. Dias, Thaís Gaudêncio, et al. Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-document corpus and an 18-query development benchmark, with one Y…https://arxiv.org/abs/2610.30755https://arxiv.org/abs/2610.30755Thu, 22 Oct 2026 00:00:00 +0000Zhengye Bao, Shengtao Zhang, Haokai Zhang, Shiqi Lou, et al. LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other complex operations. Is this complexity always necessary? We study Raw-RAG, a naive RAG baseline using dense retrieval and reranking over raw histo…https://arxiv.org/abs/2610.29722https://arxiv.org/abs/2610.29722Wed, 21 Oct 2026 00:00:00 +0000Ido Levy, Segev Shlomov, Leshem Choshen Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, reranking, query augmentation, context compression, and agentic verification, yet these techniques are typically evaluated one at a time. It remains unclear whether their is…https://arxiv.org/abs/2610.28957https://arxiv.org/abs/2610.28957Tue, 20 Oct 2026 00:00:00 +0000Juan Terven, Diana-Margarita Córdova-Esparza, Julio-Alejandro Romero-González, Edgar Chavez-Urbiola, et al. 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 uses 396 Q…https://arxiv.org/abs/2610.27816https://arxiv.org/abs/2610.27816Tue, 20 Oct 2026 00:00:00 +0000Niclas Hart, Nicolas Weeger Retrieval-Augmented Generation (RAG) has become the dominant paradigm for grounding the outputs of large language models (LLM) in external knowledge. However, practitioners are faced with a vast configuration space comprising chunking, embedding, retrieval, reranking, prompting and generation models, and there is limit…https://arxiv.org/abs/2610.26339https://arxiv.org/abs/2610.26339Mon, 19 Oct 2026 00:00:00 +0000Adrián Sánchez-Freire, Gonzalo Pérez-Gómez, Aitziber Atutxa, Ander Barrena We present a controlled, large-scale evaluation of how corpus scale, document representation, and reranking affect the effectiveness and efficiency of biomedical Retrieval-Augmented Generation (RAG) systems. Retrieval collections were progressively expanded while retaining the relevant source documents, enabling consis…https://arxiv.org/abs/2610.26313https://arxiv.org/abs/2610.26313Mon, 19 Oct 2026 00:00:00 +0000Surya Deep Singh, Ashutosh Tripathi, Gaurav Deep Singh Retrieval-Augmented Generation (RAG) can ground LLM outputs in domain-specific knowledge, but legal documents are hard: standard chunking fragments hierarchical argument structure, and generic embeddings struggle with both precise citation matching and semantic understanding. We propose StrucChunk (Structure Aware Chun…https://arxiv.org/abs/2610.26951https://arxiv.org/abs/2610.26951Sun, 18 Oct 2026 00:00:00 +0000Debopriyo Banerjee, Owais Aijaz, Ahmer Tabassum, Zhuohan Xie, et al. · EMNLP 2026 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 reference…https://arxiv.org/abs/2610.24659https://arxiv.org/abs/2610.24659Sat, 17 Oct 2026 00:00:00 +0000Omar El Bachyr, Saad Ezzini, Tegawendé F. Bissyandé, Jacques Klein Document preprocessing choices can substantially affect retrieval in Retrieval-Augmented Generation (RAG) pipelines, yet they are often selected heuristically and are difficult to compare under consistent conditions. We present RAGit, an open-source experimentation workbench for the systematic and reproducible evaluati…https://arxiv.org/abs/2610.21184https://arxiv.org/abs/2610.21184Thu, 15 Oct 2026 00:00:00 +0000Jiaqi Wei, Wenxuan Huang, Chengdong Xu, Xiang Zhang, et al. Multi-hop retrieval-augmented generation (RAG) requires an agent to retrieve evidence for a sequence of dependent sub-questions. When a wrong answer lacks a required passage, the passage may be inaccessible to the retriever, or the agent may have failed to issue a query that would retrieve it. Standard retrieval evalua…https://arxiv.org/abs/2610.19549https://arxiv.org/abs/2610.19549Wed, 14 Oct 2026 00:00:00 +0000Yining Tang, Junyu Zhang, Haomiao Qiu, Yongchao Liu, et al. Graph retrieval-augmented generation (GraphRAG) uses document-derived knowledge graphs to assemble evidence for large language model (LLM) answers. Its security depends on both the seed chunks retrieved for a query and the graph evidence assembled from them, yet attacks on this evidence path remain underexplored. We in…https://arxiv.org/abs/2610.19528https://arxiv.org/abs/2610.19528Wed, 14 Oct 2026 00:00:00 +0000Shijun Li, Yang Liu, Najmeh Sadoughi, Dongmei Wang, et al. Retrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations and terminology. However, existing retrieval-augmented machine translation systems typically apply predefined retrieval strategies uniformly across all inputs. We argue t…https://arxiv.org/abs/2610.14428https://arxiv.org/abs/2610.14428Sat, 10 Oct 2026 00:00:00 +0000Istok Bako, Bonan Min, Tiffany Shao, Claire Cheng, et al. · EMNLP 2026 Enterprise workflow automation typically requires retrieving a complete and accurate set of relevant information from large operational document corpora (SOPs, policy documents) given a specific scenario or request. In customer support (CS), for example, human specialists must determine the correct sequence of resoluti…https://arxiv.org/abs/2610.13296https://arxiv.org/abs/2610.13296Fri, 09 Oct 2026 00:00:00 +0000Cheuk Hei Chung, Li Liu High-precision retrieval over external knowledge bases is essential for LLM agents to operate effectively. However, existing Information Retrieval (IR) research primarily optimizes query-side retrievers (e.g., ColBERT, BGE) and generators (e.g., Self-RAG, GraphRAG), while reducing corpus-side representation to chunking…https://arxiv.org/abs/2610.13128https://arxiv.org/abs/2610.13128Fri, 09 Oct 2026 00:00:00 +0000Wenlin Lin, Fanzhe Wei Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents give one model both kinds of tools and let it schedule itself. We present KnowForge, a pipeline separated by job: a hybrid-retrieval knowledge-point in…https://arxiv.org/abs/2610.11727https://arxiv.org/abs/2610.11727Thu, 08 Oct 2026 00:00:00 +0000Yuxuan Chen, Mingwei Liu, Guangsheng Ou, Zekai Zhang, et al. Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific knowledge. However, adapting retrievers to evolving code repositories remains challenging due to the noise and redundancy inherent in massive code corpora. Standard fine-…https://arxiv.org/abs/2610.11370https://arxiv.org/abs/2610.11370Thu, 08 Oct 2026 00:00:00 +0000Meghanadh Pulivarthi, Swaraj Kumar Biswal, Kushagra Bhushan, Yatin Nandwani, et al. Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolated chunks without document structure, making it difficult to distinguish relevant evidence from chunks that merely resemble the query. Structure-aware methods such as Pa…https://arxiv.org/abs/2610.09412https://arxiv.org/abs/2610.09412Wed, 07 Oct 2026 00:00:00 +0000Guillaume Brouillette, Faustin Kagabo, Usef Faghihi, Nadia Ghazzali Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves retrieval and answer quality. We show that its effectiveness varies primarily with candidate-pool redundancy, in a pattern consistent with the number of distinct evidence p…https://arxiv.org/abs/2610.09361https://arxiv.org/abs/2610.09361Wed, 07 Oct 2026 00:00:00 +0000Xiaotian Qiu, Kairui Liu, Shi Chenyi, Jinyuan Deng, et al. Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents. For complex technical documentation, however, the primary bottleneck is often not model reasoning but a mismatch between a query and the way knowledge is organized for retrieval. This mismatch is pronounced in Electronic Design Automati…https://arxiv.org/abs/2610.08463https://arxiv.org/abs/2610.08463Tue, 06 Oct 2026 00:00:00 +0000Edan Kinderman, Elad Hoffer, Yochai Blau, Brian Chmiel, et al. Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtrieval And Long-Context with a Single Mode…