Latest Retrieval-Augmented Generation Research Papers
The newest Retrieval-Augmented Generation papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Retrieval-Augmented Generation so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Retrieval-Augmented Generation papers in your inbox — free →Recent papers
- ACE: An AI-Orchestrated Intrusion Detection and Compliance Mapping EngineAbdoulie Ceesay, Rishikesh Sahay, Md Rasel Al Mamun, Bell Raj Eapen · Journal of the Association ... · Aug 15, 2026
The Automated Compliance Engine (ACE) is an AI-orchestrated intrusion detection and compliance mapping engine that is designed and implemented to bridge the gap between low-level network security events and high-level regulatory requirement…
- How Students Learn with Generative AI: Evidence from Student–AI InteractionsYang Kai, Wei Zhang, Kui Du · Journal of the Association ... · Aug 15, 2026
GenAI tools have diffused rapidly across higher education and are increasingly embedded in students' everyday learning practices. However, scholarly understanding of how students actually use GenAI for learning remains limited. This project…
- EVALUATING FINE-TUNED LLMS FOR MENTAL HEALTH SUPPORT: TEXT AND AUDIO MODALITIESLakshika Vaishnav, Ram Gopal Reddy Jonnala, Sanjay Goel · Journal of the Association ... · Aug 15, 2026
Study presents a comprehensive evaluation of a mental health language model, fine-tuned on a curated dataset of questions and conversational mental health data across text and preliminary audio modalities. The dataset comprises structured i…
- Medusa:Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented GenerationYingjia Shang, Yi; id_orcid 0000-0002-0811-6150 Liu, H Wang, Feng Li et al. · CityU Scholars · Aug 1, 2026
With the rapid advancement of retrieval-augmented vision-language models, multimodal medical retrieval-augmented generation (MMed-RAG) systems are increasingly adopted in clinical decision support. These systems enhance medical applications…
- Retrieval Augmented Generation Using Multimodal Large Language Models for Real-Time Knowledge-Grounded Question AnsweringDr. K. Sujatha · Open MIND · Jul 30, 2026
The exponential growth of heterogeneous digital information across structured and unstructured repositories presents a critical challenge for large language models (LLMs): the inability to access and reason over dynamically evolving knowled…
- Retrieval Augmented Generation Using Multimodal Large Language Models for Real-Time Knowledge-Grounded Question AnsweringDr. K. Sujatha · Zenodo (CERN European Organ... · Jul 30, 2026
The exponential growth of heterogeneous digital information across structured and unstructured repositories presents a critical challenge for large language models (LLMs): the inability to access and reason over dynamically evolving knowled…
- MemTools: A Unified Research Framework for Interoperable Agent MemoryChengfeng Zhao, Jinhui Chen, Sirui Liang, Shizhu He et al. · arXiv · Jul 23, 2026
While memory systems are essential for agent architectures, pervasive architectural fragmentation restricts systematic research. Existing implementations typically couple different stages of the memory lifecycle, entangle evaluation logic w…
- GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAGPaolo Pedinotti, Enrico Santus · arXiv · Jul 23, 2026
Retrieval-Augmented Generation (RAG) systems increasingly employ multiple LLM agents. Yet, most prior work optimizes components in isolation rather than coordinating improvements across the pipeline. We introduce GRADRAG, a framework for cr…
- PrefReward: Learning User Preference Matrix for Personalized Text GenerationYue Wu, Chengbing Wang, Yimeng Bai, Xiaoyan Zhao et al. · arXiv · Jul 23, 2026
Large Language Models (LLMs) have demonstrated remarkable ability in generating personalized content by leveraging user histories and contextual cues. However, most existing personalization approaches rely on implicit representations within…
- RAQAMLI KUTUBXONALAR UCHUN CHATBOT YARATISHNING ZAMONAVIY USULLARIMadaminov Shoxruxbek Ma'rufjon oʻgʻli · Zenodo (CERN European Organ... · Jul 23, 2026
Ushbu maqolada oliy ta’lim va ilmiy-tadqiqot muassasalari raqamli kutubxonalarida foydalanuvchilarga xizmat ko‘rsatish sifatini oshirish va axborot qidiruv jarayonlarini avtomatlashtirish maqsadida chatbotlarni yaratishning zamonaviy usulla…
- RAQAMLI KUTUBXONALAR UCHUN CHATBOT YARATISHNING ZAMONAVIY USULLARIMadaminov Shoxruxbek Ma'rufjon oʻgʻli · Zenodo (CERN European Organ... · Jul 23, 2026
Ushbu maqolada oliy ta’lim va ilmiy-tadqiqot muassasalari raqamli kutubxonalarida foydalanuvchilarga xizmat ko‘rsatish sifatini oshirish va axborot qidiruv jarayonlarini avtomatlashtirish maqsadida chatbotlarni yaratishning zamonaviy usulla…
- Sound Probabilistic Safety Bounds for Large Language ModelsMahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani, Alessandro Abate · arXiv · Jul 22, 2026
We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence intervals to obtain pro…
- Self-supervision drives representational convergence in medical foundation models more than clinical supervisionSoroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia, Lisa Adams et al. · arXiv · Jul 22, 2026
Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concentrate their representations onto a shared structure. Whether this convergence is real, wha…
- OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party SkillsQiyuan Liu, Tingfeng Hui, Kun Zhan, Kaike Zhang et al. · arXiv · Jul 22, 2026
LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent safety risks that o…
- KnowPro: A Confidence-Aware Knowledge Graph Construction and Graph-RAG Retrieval Framework for Unstructured Scientific TextSwapnil Kale, Sanchit Joshi, Aaradhya Kulkarni, Vardhan Bhanuwanshe, Prof. Varsha Kulkarni · Zenodo (CERN European Organ... · Jul 22, 2026
The rapid growth of unstructured scientific literature presents significant challenges for automated knowledge acquisition and semantic querying. Existing pipelines frequently suffer from unreliable extraction, lack of traceability, and hal…
- A REVIEW OF AI-ENABLED INTELLIGENT ASSISTANTS FOR PERSONALIZED AND ADAPTIVE LEARNING IN HIGHER EDUCATIONInternational Research Jour... · Jul 22, 2026
This paper presents a novel framework, Artificial Intelligence-Enabled Intelligent Assistant (AIIA), for personalized and adaptive learning in higher education.The AIIA system leverages advanced AI and natural language processing (NLP) tech…
- CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic InterpretabilityPratinav Seth, Hem Gosalia, Aditya Kasliwal, Vinay Kumar Sankarapu · arXiv · Jul 21, 2026
Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such analyses currently requires stitching together separate implem…
- AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion DraftersYu-Yang Qian, Hao-Cong Wu, Chen Chen, Jiacheng Sun et al. · arXiv · Jul 21, 2026
Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference. Recent work su…
- AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal SystemShubham Kumar Nigam, Shubham Kumar Mishra, Noel Shallum, Kripabandhu Ghosh et al. · arXiv · Jul 21, 2026
This comprehensive study introduces an advanced Artificial Intelligence for Indian Legal Question Answering (AILQA) system tailored to the Indian legal context. AILQA leverages a variety of embedding and generative models, including recent …
- RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government AgencyDan Musetoiu · arXiv · Jul 21, 2026
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-suppor…
- Design and Implementation of a RAG-Based AI Agent for ESG ComplianceYeong-Ju Shin, Daehee Kim, Jin-hong Yang · The Journal of Korean Insti... · Jul 21, 2026
최근 ESG(Environmental, Social, Governance) 규제의 강화로 인해 기업의 공시 의무와 대응 필요성이 급격히 증가하고 있다. 그러나 ESG 관련 규제 문서는 국가·산업별로 다양하고, 복잡한 법령 구조를 지니고 있어 전문 인력이 아니면 신속한 해석이 어렵다. 본 논문에서는 이러한 문제를 해결하기 위해 Retrieval-Augmented Generation(RAG) 기반의 ESG 규제 문서 해석용 AI …
- Domain adaptation of large language models for additive manufacturing using retrieval-augmented generation and fine-tuningSaiful Islam Sagor, Tania Haghighi, Md Rahatuzzaman, Anasheh Khecho et al. · Frontiers in Manufacturing ... · Jul 21, 2026
Introduction General-purpose large language models (LLMs) often struggle to generate reliable responses in specialized engineering domains due to limited domain grounding and insufficient exposure to structured technical knowledge. This stu…
- RAGnRoll: Learning to Iteratively Retrieve and Generate Attributable Answer SnippetsHanane Djeddal, Laure Soulier, Karen Pinel-Sauvagnat, Sophia Katrenko et al. · ACM Transactions on Informa... · Jul 21, 2026
The rapid adoption of generative search engines has marked a significant shift in information retrieval. New approaches leverage Large Language Models (LLMs) to provide synthesized, contextually rich responses in natural language to directl…
- Stateful Chunking: Eliminating Redundant Enterprise RAG Costs via Content-Addressable Version ControlAnushka Patidar · Zenodo (CERN European Organ... · Jul 21, 2026
Retrieval-Augmented Generation (RAG) architectures face severe economic inefficiencies at scale due to monolithic indexing models. When document corpora undergo iteration, specifically regarding parameter adjustments in chunking strategies …
- Stateful Chunking: Eliminating Redundant Enterprise RAG Costs via Content-Addressable Version ControlAnushka Patidar · Zenodo (CERN European Organ... · Jul 21, 2026
Retrieval-Augmented Generation (RAG) architectures face severe economic inefficiencies at scale due to monolithic indexing models. When document corpora undergo iteration, specifically regarding parameter adjustments in chunking strategies …
- RAFE-XAI: A Retrieval-Augmented Feature Engineering and Explainable NLP Framework for Urban Infrastructure Risk ClassificationAbdulaziz Almaleh, Abdullah M. Alqahtani · Mathematics · Jul 21, 2026
Urban infrastructure systems increasingly depend on textual reports generated by citizens, inspection teams, maintenance units, emergency platforms, and smart city services. Accurate identification of critical risks in these reports is esse…
- Artificial Intelligence-Guided Cosolvent Design for High-Performance Perovskite/Silicon Tandem Solar CellsLu Liu, Xinying Cai, Bita Farhadi, X Q Dong et al. · Nano-Micro Letters · Jul 21, 2026
Abstract Realizing high-performance perovskite/silicon tandem solar cells requires precise control of wide-bandgap perovskite crystallization. Solvent engineering is the most direct lever for this task; yet, its intricate, multi-variable me…
- Large Language Models in High Energy Physics (Succinct Survey) and Directions of Future DevelopmentsА. Е. Шевель, A.A. Oreshkin, А. В. Швецов, A. V. Naikov · Physics of Particles and Nu... · Jul 20, 2026
Abstract Integrating Large Language Models (LLMs) into high-energy physics (HEP) drives a paradigm shift in how researchers design experiments, analyze data, and automate complex workflows. A survey reveals various scenarios in which LLMs u…
- Retrieval-Augmented Generation Architecture for Indonesian Academic Regulation Question Answering: A Microservices-Based ImplementationHendarman Lubis, Istiqoomatun Nisaa, Annas Rifa’i, Erlangga Erlangga · Journal of Intelligent Soft... · Jul 20, 2026
Indonesian higher-education institutions operate under a dense and frequently updated body of academic regulations—national standards, institutional statutes, and study-program handbooks—that students and staff must consult accurately. Gene…
- AGORA-BIM: An Agentic, Retrieval-Augmented and Spatially-Aware Framework for Natural Language Querying of BIM Knowledge GraphsWijang Widhiarso, Alfiarini Alfiarini, Dytha Ananda Widhiarso, Jamaludi Salim · Journal of Intelligent Soft... · Jul 20, 2026
Building Information Modeling (BIM) consolidates heterogeneous building information into a single digital model, yet retrieving meaningful insights from Industry Foundation Classes (IFC) files remains difficult and demands specialised exper…