https://ym-xu.github.io/living-survey/fields/rag/A daily-updated map of retrieval-augmented generation research.enThu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2611.14355https://arxiv.org/abs/2611.14355Tue, 10 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>S M Rayeed, Charles V. Stewart, Yao Ma</b></p><p>Retrieval-augmented systems often retrieve passages that are accurate and relevant but state the answer at a coarser level of granularity than the question requires. For example, a question may ask which specific disease a drug treats (familial hyperlipidemia), while the retrieved passage mentions the broader disease f…</p>https://arxiv.org/abs/2611.14263https://arxiv.org/abs/2611.14263Tue, 10 Nov 2026 00:00:00 +0000Evaluation & FaithfulnessRAG Systems & Applications<p><b>Wenqi Zhou, Leonardo Baldo, Kai Goebel, Manuel Arias Chao</b></p><p>Fault diagnosis in complex systems requires linking observed changes in physical quantities to the failure mechanisms that produce them. Experienced engineers perform this task by combining sensor information with knowledge of system behavior and fault propagation. Large Language Models (LLMs) can support this process,…</p>https://arxiv.org/abs/2611.13675https://arxiv.org/abs/2611.13675Tue, 10 Nov 2026 00:00:00 +0000Efficiency & Long ContextMultimodal RAGRAG Systems & Applications<p><b>Senhao Liu, Yuheng Zhang, Chunyu Wei, Yueguo Chen, et al.</b> · <i>NeurIPS 2026</i> · <a href="https://github.com/brighterr/OpticalRAG">code</a></p><p>Retrieval-augmented generation (RAG) is bottlenecked by the token budget of large language models: feeding long documents into the context window is expensive, while aggressive textual compression discards fine-grained information that is irreversibly lost in a one-dimensional token sequence. We argue that this bottlen…</p>https://arxiv.org/abs/2611.11960https://arxiv.org/abs/2611.11960Mon, 09 Nov 2026 00:00:00 +0000Multimodal RAGEvaluation & FaithfulnessRAG Systems & Applications<p><b>Guoqing Zhang, Rafik Hadfi, Takayuki Ito</b> · <a href="https://github.com/KuoChing-cmd/ClinicalNoteAgent/">code</a></p><p>Unplanned 30-day intensive care unit (ICU) readmission is a critical benchmark for evaluating healthcare quality. Most predictive models assume readmission risk depends solely on a patient's individual pathophysiological state, ignoring hospital operational context and resource capacity. In practice, discharge decision…</p>https://arxiv.org/abs/2611.11771https://arxiv.org/abs/2611.11771Mon, 09 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Yan Wang, Yuxin Zhang, Shenyu Zhang, Yongrui Chen, et al.</b></p><p>Retrieval-Augmented Generation (RAG) systems have demonstrated remarkable effectiveness in mitigating hallucinations by incorporating external knowledge. However, the retrieval process inevitably introduces noise, posing significant challenges to RAG robustness. Fundamentally, noise robustness is a composite competency…</p>https://arxiv.org/abs/2611.11349https://arxiv.org/abs/2611.11349Sun, 08 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Qinjiang Niu, Lu Yan</b></p><p>The rapid growth of scientific literature and the high heterogeneity of biological terminology and mechanistic descriptions make it difficult for researchers to integrate scattered research evidence, identify connections among biological events, and construct mechanistic networks. Here, we developed a high-throughput h…</p>https://arxiv.org/abs/2611.11113https://arxiv.org/abs/2611.11113Sun, 08 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Linyao Zheng, Xuhang Shi, Zhifang Mao, Chongqi Qu, et al.</b></p><p>Complex Web question answering requires retrieval-augmented generation (RAG) systems to identify target entities from multi-clue descriptions and connect evidence scattered across long Web pages. Individual pages often support only some of the required semantic constraints, while clues discovered on one page guide subs…</p>https://arxiv.org/abs/2611.11010https://arxiv.org/abs/2611.11010Sat, 07 Nov 2026 00:00:00 +0000Graphs & Knowledge BasesRetrievers & IndexingRAG Systems & Applications<p><b>Uday Allu</b> · <a href="https://github.com/udayallu-ml/Lightfoot-GraphRAG">code</a></p><p>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…</p>https://arxiv.org/abs/2611.10894https://arxiv.org/abs/2611.10894Sat, 07 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Subin Kim, Anh-Quan Pham, Dinesh Jayaraman</b></p><p>Pre-training large parametric "Vision-Language-Action" (VLA) models on large demonstration datasets has recently yielded promising results for general-purpose manipulation. However, these models still struggle under even small domain shifts relative to the training data, such as changes in camera viewpoint, background,…</p>https://arxiv.org/abs/2611.10657https://arxiv.org/abs/2611.10657Sat, 07 Nov 2026 00:00:00 +0000Agentic & Iterative RAGMultimodal RAGEfficiency & Long ContextRAG Systems & Applications<p><b>Haoran Luo, Ziyue Zhu, Shangyang Wu, Linhao Luo, et al.</b> · <i>NeurIPS 2026</i> · <a href="https://github.com/LHRLAB/MMGraph-Agent">code</a></p><p>Driven by increasingly complex real-world applications, Retrieval-Augmented Generation (RAG) has evolved from textual pipelines to multimodal settings, comprising two complementary dimensions: knowledge organization and retrieval enhancement. However, existing methods still face challenges of high construction cost, co…</p>https://arxiv.org/abs/2611.10477https://arxiv.org/abs/2611.10477Sat, 07 Nov 2026 00:00:00 +0000Agentic & Iterative RAGRAG Systems & Applications<p><b>Yi Ge, Heng Huang</b> · <i>NeurIPS 2026</i> · <a href="https://github.com/EllenYiGe/PatternBloom">code</a></p><p>Reinforcement-learning-trained agents for retrieval-augmented generation retrieve content (passages, knowledge-graph fragments, or hyperedges) and supervise training with outcome rewards on the final answer. Across these paradigms the reasoning route through retrieved content never leaves the language model's hidden st…</p>https://arxiv.org/abs/2611.10405https://arxiv.org/abs/2611.10405Sat, 07 Nov 2026 00:00:00 +0000Retrievers & IndexingRAG Systems & Applications<p><b>Hongyuan Xu, Dezhi Ye, Jiahao Cao, Jie Liu, et al.</b></p><p>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…</p>https://arxiv.org/abs/2611.10335https://arxiv.org/abs/2611.10335Sat, 07 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Ben Jenkins, Mihaela Cardei</b></p><p>Retrieval-augmented generation (RAG) can surface passages that support a claim, contradict it, or fail to address it, yet existing calibrated grounding methods are typically one-sided and model only supporting evidence. We introduce Conformal Evidence Sets (CES), a two-sided framework that returns separate support and …</p>https://arxiv.org/abs/2611.09866https://arxiv.org/abs/2611.09866Fri, 06 Nov 2026 00:00:00 +0000Graphs & Knowledge BasesRAG Systems & Applications<p><b>Rochak Dhakal, Chen Zhao, Soup Cobb, Xin Qian, et al.</b></p><p>Purpose: Surgical operative reports support procedural documentation, surgical training, performance assessment, and workflow review. However, extracting meaningful information often requires extensive manual review and clinical expertise. Automated surgical scene descriptions could reduce this burden by leveraging rec…</p>https://arxiv.org/abs/2611.09807https://arxiv.org/abs/2611.09807Fri, 06 Nov 2026 00:00:00 +0000Evaluation & FaithfulnessRAG Systems & Applications<p><b>Osamudiamen Edogun, Joshua Obigwe, Irfan Mehmood</b> · <a href="https://github.com/BigBrown10/nmafc-paper">code</a></p><p>A conversational agent that remembers has to decide what to keep. Retrieval-augmented generation keeps the transcript and searches it; the alternative is to compact each turn into atomic facts and search those. We compare the two on LoCoMo, with both arms answering all 1,985 questions in one window, against the same st…</p>https://arxiv.org/abs/2611.09791https://arxiv.org/abs/2611.09791Fri, 06 Nov 2026 00:00:00 +0000RAG Systems & ApplicationsEvaluation & Faithfulness<p><b>Gabriel Souza Baggio, Gabriel Machado Lunardi, Guilherme Medeiros Machado, Subhankar Maity, et al.</b></p><p>Competitive programming problems pose distinctive challenges for Large Language Models, as they demand not only proficient code generation but also advanced algorithmic reasoning. This study presents a Retrieval-Augmented Generation approach specifically designed to enhance the capacity of Large Language Models to addr…</p>https://arxiv.org/abs/2611.09658https://arxiv.org/abs/2611.09658Fri, 06 Nov 2026 00:00:00 +0000Graphs & Knowledge Bases<p><b>Jie Fu, Yuan Hong, Yue Ning, Wendy Hui Wang</b></p><p>Graph Retrieval-Augmented Generation (GraphRAG) connects information across documents through entity relationships to support relational reasoning. However, black-box access to GraphRAG systems can enable adversaries to reconstruct knowledge graphs and recover both structural connectivity between entities and the seman…</p>https://arxiv.org/abs/2611.09423https://arxiv.org/abs/2611.09423Fri, 06 Nov 2026 00:00:00 +0000Agentic & Iterative RAGEvaluation & FaithfulnessRAG Systems & Applications<p><b>Sofia Campos, Carlos Martins, Pedro Pires, João Gama, et al.</b></p><p>In the healthcare sector, claim denials impose significant financial and administrative burdens, emphasizing the need for automated and trustworthy decision-support systems. This paper proposes a modular Agentic Artificial Intelligence (AI) framework for healthcare claim denial analysis, integrating specialized agents …</p>https://arxiv.org/abs/2611.09414https://arxiv.org/abs/2611.09414Fri, 06 Nov 2026 00:00:00 +0000Agentic & Iterative RAGGraphs & Knowledge Bases<p><b>Rosario Napoli, Antonio Celesti, Massimo Villari, Maria Fazio</b></p><p>Knowledge Graphs (KGs) and Large Language Models (LLMs) represent two approaches for knowledge representation and reasoning over heterogeneous data. Recent research has explored their integration through Graph Retrieval-Augmented Generation (GraphRAG) systems, which use KGs to provide structured context to LLMs. Howeve…</p>https://arxiv.org/abs/2611.09407https://arxiv.org/abs/2611.09407Fri, 06 Nov 2026 00:00:00 +0000RAG Systems & ApplicationsAgentic & Iterative RAG<p><b>Ye Zihao, Lin Xiaoheng</b></p><p>Large language models (LLMs) can draft plausible travel itineraries, but the plans they produce are frequently infeasible: attractions are grouped into days without regard for geography, opening hours are ignored, and a single generation pass cannot reliably organize a multi-day trip. We present ROAM, a retrieval-augme…</p>https://arxiv.org/abs/2611.09298https://arxiv.org/abs/2611.09298Fri, 06 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Oliver Noll, Nicholas Tan Jerome, Alexander Lehnen, Frank Simon, et al.</b></p><p>Long-term particle physics experiments face critical operational challenges: monitoring non-stationary machine data streams and preserving tacit expert knowledge. We present the "Helmholtz Co-Pilot," a hybrid Multi-Agent System (MAS) acting as an autonomous experiment steward. The system can be triggered interactively …</p>https://arxiv.org/abs/2611.09232https://arxiv.org/abs/2611.09232Fri, 06 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Lorenzo Mannocci, Francesca Naretto, Lucia Passaro, Anna Monreale</b></p><p>Artificial Intelligence (AI) is increasingly embedded in high-risks decision-making systems across domains such as healthcare, finance, and the judicial system. As reliance on predictive models grows, so does the demand for Explainable AI (XAI) to ensure transparency, trust, and interpretability. However, existing XAI …</p>https://arxiv.org/abs/2611.08935https://arxiv.org/abs/2611.08935Fri, 06 Nov 2026 00:00:00 +0000Agentic & Iterative RAGRAG Systems & ApplicationsMultimodal RAG<p><b>Jing Hao, Weinan Zhou, Zhihong Lu, Yaling Shen, et al.</b></p><p>Reliable dermatology AI requires access to verifiable evidence distributed across heterogeneous textual and visual sources. However, conventional retrieval-augmented generation (RAG) typically relies on one-shot retrieval from flat corpora, limiting its ability to adapt retrieval granularity, explore multi-hop relation…</p>https://arxiv.org/abs/2611.07928https://arxiv.org/abs/2611.07928Thu, 05 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Petru Neague, Quinten Stokkink, Martijn de Vos, Rafael Pires, et al.</b></p><p>Retrieval-augmented generation (RAG) is a standard approach to enhance the reliability of large language model (LLM) outputs by retrieving documents relevant to a query and supplying them in the LLM prompt. Today's RAG systems collect, index, and serve these documents from centralized stores. In practice, however, docu…</p>https://arxiv.org/abs/2611.07393https://arxiv.org/abs/2611.07393Thu, 05 Nov 2026 00:00:00 +0000Efficiency & Long ContextRAG Systems & ApplicationsAgentic & Iterative RAG<p><b>Vihan Lakshman, Peter Baile Chen, Zhuohan Gu, Michael Cafarella</b> · <i>CIKM 2026 Workshop</i></p><p>Recent work in machine learning has demonstrated that transformer-based language model agents can communicate state not only through text, but also directly in latent space via key-value (KV) caches. In this paper, we argue that such cache-to-cache translation can provide utility beyond the original motivating applicat…</p>https://arxiv.org/abs/2611.06715https://arxiv.org/abs/2611.06715Wed, 04 Nov 2026 00:00:00 +0000Evaluation & FaithfulnessRAG Systems & Applications<p><b>Zohreh Abbasi Liasi, Batoul Hammoud, Anas Madkoor, Ehsaneddin Asgari</b> · <a href="https://huggingface.co/spaces/QCRI/non-parametric-memory-relational-reasoning">code</a></p><p>Retrieval-augmented generation (RAG) assumes that language models can reason over relations stated in their context rather than fall back on associations memorized during pretraining. We study this evidence-conditioned relational reasoning in isolation, with the facts supplied directly in the prompt rather than retriev…</p>https://arxiv.org/abs/2611.06498https://arxiv.org/abs/2611.06498Wed, 04 Nov 2026 00:00:00 +0000Retrievers & IndexingRAG Systems & ApplicationsEfficiency & Long Context<p><b>Georgios Feretzakis, Alexandros Papaspyridis</b> · <a href="https://github.com/securagenai/signed-but-steerable">code</a></p><p>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…</p>https://arxiv.org/abs/2611.06481https://arxiv.org/abs/2611.06481Wed, 04 Nov 2026 00:00:00 +0000Graphs & Knowledge BasesAgentic & Iterative RAGRetrievers & Indexing<p><b>Jyotin Goel, Abhinav Arun, Tejas Prakash Agarwal, Bhaskarjit Sarmah, et al.</b></p><p>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…</p>https://arxiv.org/abs/2611.06170https://arxiv.org/abs/2611.06170Wed, 04 Nov 2026 00:00:00 +0000Efficiency & Long ContextRAG Systems & Applications<p><b>Pragyan Phukan</b></p><p>While Large Language Models (LLMs) excel in high-resource languages, their performance often degrades in low-resource languages due to tokenization inefficiencies, generative instability, and linguistic interference. This paper presents AssameseLM-E2B and its instruction-tuned variant, AssameseLM-E2B-it, a 2-billion-pa…</p>https://arxiv.org/abs/2611.05900https://arxiv.org/abs/2611.05900Wed, 04 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Linyao Zheng, Zhifang Mao, Xuhang Shi</b></p><p>Personalized retrieval-augmented generation requires extracting and applying user preferences from extended interaction histories. This task is challenging because preference evidence is scattered across past conversations and remains bound to specific temporal and situational contexts. Consequently, isolated fragments…</p>https://arxiv.org/abs/2611.04949https://arxiv.org/abs/2611.04949Tue, 03 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Dayeon Jeong, Kyeongpil Kang</b> · <i>EMNLP 2026 Findings</i></p><p>Historical archives are invaluable for multidisciplinary research but remain inaccessible globally due to severe language barriers. While manual translation is prohibitively expensive and time-consuming, simply applying existing machine translation models is inadequate due to unique linguistic nuances and the temporal …</p>https://arxiv.org/abs/2611.04625https://arxiv.org/abs/2611.04625Tue, 03 Nov 2026 00:00:00 +0000Agentic & Iterative RAGRetrievers & IndexingRAG Systems & Applications<p><b>Manzong Huang, Chenyang Bu, Yi He, Jiapu Wang, et al.</b></p><p>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…</p>https://arxiv.org/abs/2611.04264https://arxiv.org/abs/2611.04264Tue, 03 Nov 2026 00:00:00 +0000RAG Systems & ApplicationsRetrievers & Indexing<p><b>Janet Sung, Kainan Zhou, Gangzhen Qian, Hang Xiao, et al.</b></p><p>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…</p>https://arxiv.org/abs/2611.03747https://arxiv.org/abs/2611.03747Mon, 02 Nov 2026 00:00:00 +0000RAG Systems & ApplicationsEvaluation & Faithfulness<p><b>Huan Phong Thai, Thu Anh Ngoc Le, Nhu Huynh Thi Le, Nhan Huu Tran, et al.</b></p><p>Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-based systems often struggle with maintaining contextual accuracy and generating relevant responses in dynamic financial environments. To addres…</p>https://arxiv.org/abs/2611.03744https://arxiv.org/abs/2611.03744Mon, 02 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Mehrnoush Mohammadi, Kamal Berahmand, Mohammad Morsali, Shazia Sadiq, et al.</b></p><p>Knowledge tracing (KT) estimates learners' evolving knowledge states from interaction histories to support adaptive learning. Retrieval-augmented KT improves these estimates using cross-learner behavioral evidence, but existing approaches typically separate evidence retrieval from downstream prediction. This creates a …</p>https://arxiv.org/abs/2611.02883https://arxiv.org/abs/2611.02883Mon, 02 Nov 2026 00:00:00 +0000RAG Systems & Applications<p><b>Zuguang He, Congcong Zheng, Wanyue Chen, Wenya Zhou, et al.</b></p><p>Reclamation of saline-alkali land requires management plans that account for soil and water conditions, treatment evidence, and financial constraints. This study develops Wenyao, an agricultural decision-support system integrating domain adaptation with retrieval-augmented generation. A bilingual corpus of 8,664 resear…</p>https://arxiv.org/abs/2611.02810https://arxiv.org/abs/2611.02810Mon, 02 Nov 2026 00:00:00 +0000RAG Systems & ApplicationsAgentic & Iterative RAGEvaluation & Faithfulness<p><b>Yingtao Ren, Xiao Luo, Yiwei Fu, Jinzhao Zhou, et al.</b> · <i>EMNLP 2026</i> · <a href="https://github.com/yingtaoren/TRIO">code</a></p><p>This paper studies retrieval-augmented generation (RAG), which leverages external knowledge to improve the performance of language models. Despite the remarkable progress, current RAG approaches are still far from satisfactory due to inadequate retrieval and potential hallucinations. Towards this end, we propose a nove…</p>https://arxiv.org/abs/2611.02387https://arxiv.org/abs/2611.02387Mon, 02 Nov 2026 00:00:00 +0000Retrievers & IndexingEfficiency & Long ContextRAG Systems & Applications<p><b>Yibo Wang, Jisheng Dang, Bimei Wang, Jiongpei Hou, et al.</b> · <a href="https://github.com/YiboWang2002/EviCast">code</a></p><p>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…</p>https://arxiv.org/abs/2611.03725https://arxiv.org/abs/2611.03725Sun, 01 Nov 2026 00:00:00 +0000RAG Systems & ApplicationsEvaluation & Faithfulness<p><b>Hira Naveed, Scott Barnett, Stefanus Kurniawan, John Grundy, et al.</b></p><p>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 remain u…</p>https://arxiv.org/abs/2611.02286https://arxiv.org/abs/2611.02286Sun, 01 Nov 2026 00:00:00 +0000Agentic & Iterative RAGRAG Systems & Applications<p><b>Ahmet Bahaddin Ersoz, Justin McHenry, Yevgeniya Kovalchuk, Edward Barrett, et al.</b></p><p>The rise of agentic artificial intelligence (AI) in the built environment is shifting attention from isolated AI tools toward autonomous systems that reason, plan, and act across project and organizational workflows. The effectiveness of such systems depends not only on large language model capabilities, but also on th…</p>https://arxiv.org/abs/2611.01910https://arxiv.org/abs/2611.01910Sun, 01 Nov 2026 00:00:00 +0000Evaluation & FaithfulnessAgentic & Iterative RAGRAG Systems & Applications<p><b>Sonam Gupta, Vignesh P, Vishwajeet Kumar, Adnan Qidwai, et al.</b></p><p>Retrieval-Augmented Generation (RAG) for multi-hop reasoning requires retrieval to adapt as intermediate evidence reveals new information needs. Existing approaches support such retrieval through explicit graph structures or iterative query reformulation, introducing graph-construction or query-time overhead. We presen…</p>https://arxiv.org/abs/2611.01409https://arxiv.org/abs/2611.01409Sun, 01 Nov 2026 00:00:00 +0000RAG Systems & ApplicationsMultimodal RAGEvaluation & Faithfulness<p><b>Elyas Irankhah, Shahed Salehzehi, Parisa Hosseini</b> · <a href="https://github.com/Elyasirankhah/RAG-TRACE">code</a></p><p>Purpose: Retrieval-augmented generation (RAG) can introduce electrocardiogram (ECG) criteria that lack patient-specific measurement support. This study evaluates the reliability of retrieved diagnostic criteria in AI-generated ECG reports. Methods: We analyzed 1,083 human-validated PTB-XL patient records using a librar…</p>https://arxiv.org/abs/2611.00871https://arxiv.org/abs/2611.00871Sat, 31 Oct 2026 00:00:00 +0000Evaluation & FaithfulnessRAG Systems & Applications<p><b>Youmin Ko, Jihong Jeong, Hyunjoon Kim</b> · <i>NeurIPS 2026</i></p><p>Despite advances in retrieval-augmented generation (RAG), suppressing hallucinations during complex reasoning remains a persistent challenge. We identify that existing RAG pipelines suffer from a textual bottleneck: by passing only raw text to the generator, they discard discriminative signals of the retriever. Further…</p>https://arxiv.org/abs/2611.00752https://arxiv.org/abs/2611.00752Sat, 31 Oct 2026 00:00:00 +0000RAG Systems & Applications<p><b>Dipto Sumit, Syeda Fabiayee Jahan, Farig Sadeque</b></p><p>Many questions about a book can only be answered by connecting passages chapters apart, such as a cough heard three times across a horse's life. We introduce CrossChapterQA, 1,853 such questions over 14 public-domain books. Each question lists the two to six chapters it needs (spanning half the book at the median) and …</p>https://arxiv.org/abs/2611.00450https://arxiv.org/abs/2611.00450Fri, 30 Oct 2026 00:00:00 +0000RAG Systems & Applications<p><b>Changjiang Han, Bowei He, Ye Yuan, Weixu Zhang, et al.</b> · <a href="https://github.com/SSRand/From-Lookups-to-Lessons">code</a></p><p>Retrieval-augmented generation (RAG) helps large language models (LLMs) answer factual questions beyond their training data, but it adds storage and inference costs. Distilling previously retrieved information into parametric memories enables reuse without online retrieval. However, training the memory to mimic a retri…</p>https://arxiv.org/abs/2611.00344https://arxiv.org/abs/2611.00344Fri, 30 Oct 2026 00:00:00 +0000Evaluation & FaithfulnessRAG Systems & Applications<p><b>Dmytro Kurdydyk, Aadi Palnitkar, Sebastian Scherer, Seungchan Kim</b></p><p>Retrieval-augmented generation (RAG) systems have seen growing adoption in embodied settings as language-queryable memories of the environment. However, existing approaches often assume a reliable single-episode knowledge base (KB) or accumulate observations across episodes without correcting prior errors. Such errors …</p>https://arxiv.org/abs/2610.42068https://arxiv.org/abs/2610.42068Fri, 30 Oct 2026 00:00:00 +0000Agentic & Iterative RAGEfficiency & Long ContextRAG Systems & Applications<p><b>Xin Ming Li, Peng Hu</b></p><p>Low-Earth orbit (LEO) satellite networks present a challenging routing environment due to rapidly changing topology, traffic, and link conditions. Existing deep reinforcement learning (DRL) routing methods typically rely on current observations and information encoded in network weights, limiting their ability to explo…</p>https://arxiv.org/abs/2610.41390https://arxiv.org/abs/2610.41390Fri, 30 Oct 2026 00:00:00 +0000RAG Systems & Applications<p><b>Eunsang Lee, Taein Ju, Jiyoung Lee</b> · <a href="https://github.com/ewha-mmai/audiohelix">code</a></p><p>Large audio language models (LALMs) struggle with long-form audio reasoning, as processing entire recordings often limits to capture query-relevant content distributed across distant segments while incurring substantial computational cost. We introduce AudioHelix, a hierarchical DualGraph framework tailored for LALMs' …</p>https://arxiv.org/abs/2610.41335https://arxiv.org/abs/2610.41335Fri, 30 Oct 2026 00:00:00 +0000Multimodal RAGRAG Systems & ApplicationsRetrievers & Indexing<p><b>Ziniu Liu, Xiaoyang Chen, Dezhi Ye, Jie Liu, et al.</b></p><p>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…</p>https://arxiv.org/abs/2610.41012https://arxiv.org/abs/2610.41012Thu, 29 Oct 2026 00:00:00 +0000RAG Systems & Applications<p><b>Mehrdad Ghassabi, Audrina Ebrahimi, Zahra Zojaji, Amin Milani Fard</b></p><p>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 seed 38…</p>https://arxiv.org/abs/2610.40971https://arxiv.org/abs/2610.40971Thu, 29 Oct 2026 00:00:00 +0000Graphs & Knowledge BasesMultimodal RAG<p><b>Jiacheng Ding, Yanliang Qi, Cong Guo, Peihua Mai</b></p><p>We present FieldGuideRAG, a training-free GraphRAG method in which a vision-language model, or VLM, recognizes fine-grained species by comparing the query with real photographs stored on the nodes of a knowledge graph. Multimodal GraphRAG systems describe each entity in text, and text conveys little of the visual detai…</p>https://arxiv.org/abs/2610.40966https://arxiv.org/abs/2610.40966Thu, 29 Oct 2026 00:00:00 +0000Retrievers & IndexingEvaluation & FaithfulnessRAG Systems & Applications<p><b>Ivan Kochergin, Vasily Konovalov</b></p><p>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…</p>https://arxiv.org/abs/2610.40742https://arxiv.org/abs/2610.40742Thu, 29 Oct 2026 00:00:00 +0000RAG Systems & ApplicationsEvaluation & Faithfulness<p><b>Chahana Dahal, Zuobin Xiong</b> · <a href="https://github.com/chxhana/aligned-rag-eval">code</a></p><p>Retrieval-Augmented Generation (RAG) is vulnerable to knowledge poisoning, where adversaries manipulate retrieved evidence to influence model outputs. Existing defenses are primarily evaluated using attack success rate (ASR), which obscures defense-induced failures and the mechanisms behind apparent attack prevention. …</p>https://arxiv.org/abs/2610.40409https://arxiv.org/abs/2610.40409Thu, 29 Oct 2026 00:00:00 +0000Retrievers & IndexingAgentic & Iterative RAGRAG Systems & Applications<p><b>Chenjie Qiu, Zixuan Zeng, Shaobin Shi, Bingfeng Chen, et al.</b></p><p>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…</p>https://arxiv.org/abs/2610.40314https://arxiv.org/abs/2610.40314Thu, 29 Oct 2026 00:00:00 +0000RAG Systems & Applications<p><b>He Tu, Aleena Bosco Kurumthottam, Torsten Suel</b></p><p>Retrieval-augmented generation (RAG) grounds a language model's output in retrieved evidence, but for complex questions spanning multiple aspects of an information need, relevance-based retrieval may return redundant evidence while leaving some aspects unsupported. We propose a coverage-aware retrieval pipeline that de…</p>https://arxiv.org/abs/2610.39671https://arxiv.org/abs/2610.39671Thu, 29 Oct 2026 00:00:00 +0000Agentic & Iterative RAGEfficiency & Long ContextRAG Systems & Applications<p><b>Lingkai Kong, Yuzhe Gu, Haiteng Zhao, Zijian Wu, et al.</b></p><p>Large language models (LLMs) draw on parametric knowledge and retrieval-augmented generation (RAG) to solve knowledge-intensive tasks. Yet problem solving in unfamiliar domains calls for tightly coupled knowledge acquisition and reasoning, beyond factual retrieval and aggregation or learning solely from a preassembled …</p>https://arxiv.org/abs/2610.39231https://arxiv.org/abs/2610.39231Thu, 29 Oct 2026 00:00:00 +0000Evaluation & FaithfulnessAgentic & Iterative RAGRAG Systems & Applications<p><b>Siqing Huo, Andrew Parry, Debasis Ganguly, Mark Smucker, et al.</b></p><p>Recent systems applying retrieval-augmented generation (RAG) and "deep research" iteratively generate queries, retrieve documents, and examine their contents, using the resulting information to guide subsequent search steps. When this process is carried out autonomously rather than by a human searcher, the system must …</p>https://arxiv.org/abs/2610.38366https://arxiv.org/abs/2610.38366Wed, 28 Oct 2026 00:00:00 +0000RAG Systems & ApplicationsGraphs & Knowledge Bases<p><b>Xinxun Zhang, Yuxiang Wang, Shanshan Feng, Jun Zhang, et al.</b></p><p>Recent advances in large language models (LLMs) have spurred growing interest in temporal knowledge graph question answering (TKGQA). Most existing methods rely on semantic retrieval augmented generation (RAG), which suffers from fundamental limitations in complex temporal reasoning. On the one hand, semantic-based RAG…</p>https://arxiv.org/abs/2610.38120https://arxiv.org/abs/2610.38120Wed, 28 Oct 2026 00:00:00 +0000RAG Systems & Applications<p><b>Basel Shbita, Michael Hind, Chad DeLuca, Nathan Fulton, et al.</b></p><p>Large Language Models (LLMs) treat all context tokens uniformly, lacking explicit separation between executable instructions and passive data. This leads to prompt injection vulnerabilities, ambiguous instruction binding, and unreliable execution control. We present a post-training methodology using LLMON (LLM Object N…</p>https://arxiv.org/abs/2610.37962https://arxiv.org/abs/2610.37962Tue, 27 Oct 2026 00:00:00 +0000Evaluation & FaithfulnessRAG Systems & Applications<p><b>Carlos Peláez-González, Francisco Herrera, Andrés Herrera-Poyatos</b></p><p>Large Language Models (LLMs) are increasingly used as recommendation generators in conversational recommender systems (RS) via retrieval-augmented generation (RAG). This flexible design introduces new sources of structural bias. This paper studies positional bias in top-1 and single-turn LLM-based RS: systematic depend…</p>