AgentFlareScholar · retrieval augmented generation
Retrieval-Augmented Generation: Research Digest
10 foundational papers with 46,470 combined citations, plus the latest arXiv preprints.
AISA Scholar API · arXiv
You're reading the full report — free for humans and search engines.
The same content ships as a structured JSON dataset (normalized facts, sources and
citation arrays, no HTML parsing) so AI agents can consume it directly — metered per fetch via the open
HTTP 402 payment protocol.
crawlerAutoPrice=true · verify at https://esa.aisa.one/api/v1/access/verify
What’s new on arXiv
Private Retrieval Augmented Generation via Random Projection
Dixi Yao, Tahseen Rabbani, Tian Li
Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it can also introduce privacy risks by leaking sensitive information from the retrieval datastore. We propose a simple method to preserve datastore privacy in RAG systems via random projection. By applying the same projection to both datastore embeddings and query embeddings, our method provably preserves semantic similarity between queries and retrieved items while substantially mitigating data extraction attacks. Across multiple RAG architectures and datasets, we show that this lightweight approach achieves superior retrieval and generation performance compared to prior methods which leverage formal differential privacy (DP) guarantees, while exhibiting comparable empirical privacy under strong attack models. Our results for the first time suggest that random projection can serve as a competitive and practical baseline for privacy-preserving RAG systems.
Multi-sourced AI Tutor for Non-Native English Speaker Students
Yiyin Shen, Xinyi Ai, Weibing Wang, Rogers Jeffrey Leo John, Meenakshi Syamkumar
Large language models (LLMs) are increasingly being adopted as teaching tools in computing education, particularly for developing AI tutors capable of answering student questions. With the rise in enrollment of international students in computing programs, researchers have begun to explore the difficulties that non-native English speaker (NNES) students face in computing courses due to language barriers. To aid such students, we developed a general-purpose AI tutor system that can process student questions in foreign languages (currently focused on Mandarin) and provide bilingual responses. Our system also incorporates the functionality of generating a glossary of technical terms and their explanations to enhance comprehension. Our approach utilizes a specialized Retrieval-Augmented Generation (RAG) pipeline with a novel question extraction mechanism, enabling us to effectively utilize a diverse array of course materials for answering student queries. We evaluated our AI tutor using 91 Piazza posts, demonstrating that it could answer 83.52% of the posts correctly and in a helpful manner. The tutor also provided high-quality translations for 76.92% of the questions and generated technical term glossaries for 64.47% of them. Our findings underscore the potential of multi-source RAG pipeline in enhancing AI tutor systems, offering support for non-native speakers that are challenging to provide with traditional supporting staff of a computing course.
CARA: Causally Guided Retrieval Agent for Question Answering
Weicheng Liu, Xiangcheng Wu, Depeng Xu, Haopeng Zhang, Xi Niu
Retrieval-augmented generation over text-rich knowledge graphs requires identifying evidence that contributes to answering a question, rather than merely matching its textual content. Existing agentic retrievers adaptively balance global search and multi-hop exploration but primarily rely on textual similarity to guide retrieval. We propose CARA, a training-free, CAusally guided Retrieval Agent that explicitly evaluates the causal relevance of retrieved evidence through two complementary criteria: consequentiality, measuring whether adding evidence improves answerability, and essentiality, assessing whether removing evidence weakens answerability. CARA integrates these assessments with path consistency to guide graph exploration and employs reciprocal rank fusion to aggregate evidence from multiple agents. We evaluate CARA on three STaRK datasets and augment STaRK with ground-truth answers to enable downstream question answering evaluation. Experimental results demonstrate that CARA consistently outperforms existing retrievers. CARA also improves answer quality and faithfulness while examining fewer graph nodes and requiring fewer retrieval operations. These findings demonstrate that causal relevance assessment enables more focused and effective agentic graph retrieval, improving both retrieval performance and downstream question answering.
TEM: Temporal State Tracking Memory for Large Language Model Agents
Pengfeng Song, Yunkai Zhuang, Liye Shi
An agent's memory must remain useful as information changes across conversations. A new fact may replace an earlier value without making that value irrelevant to a later question. We present Temporal State Tracking Memory (TEM), a training-free framework for tracking these changes. TEM stores facts as versioned records linked to their sources. It retrieves relevant versions, places them in source order and labels historical records before passing the evidence to the answer model. Event memory and original dialogue turns provide details missing from structured facts. We evaluated TEM on 420 questions drawn from 600 sessions involving 60 personas. Across four open-weight models, key-entity hit rates reached 75.71-97.62% overall and 96.67-100.00% on the historical-residence subset. Adding historical labels to otherwise identical, source-ordered facts increased overall hit rates by 17.14-55.95 percentage points. The evidence was compact: 94-118 tokens per answer, or 48.75-56.73% less than session-aware retrieval-augmented generation (RAG). A further evaluation on 1,540 LoCoMo questions tested hybrid memory under a fixed evidence budget. TEM exceeded session-aware RAG with both backbones; conservative score differences were 7.92 and 10.58 percentage points. The results support preserving fact versions and exposing their temporal status to the generator when answering questions about repeatedly updated information.
Loud and Clear: Making Visual Evidence Count in Multimodal Document RAG
Eunchan Jo, Seounghyun Jang, Sangwoo Mo
Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its answers depend on how well a vision-language model reads the retrieved pages. We find that evidence in retrieved pages remains underused even when the correct pages are retrieved. On SciEGQA oracle pages, five prior methods give the generator 0.7K to 2.7K visual tokens per query on average under a common image processor, yet raising the page-only budget from 1K to 32K improves accuracy by 15.22 points. At a fixed 16K budget, adding ground-truth crops improves accuracy by 3.75 points over page-only input. We study what the generator needs from retrieved pages through two requirements: Loud, making full use of visual token capacity, and Clear, refining the page so that its evidence becomes prominent. For Loud, increasing either the visual token budget or visual fidelity, the image resolution those tokens preserve, improves accuracy with the other held fixed, and full-page scaling outperforms repetition and tiling at matched budgets. For Clear, suppressing surrounding content improves accuracy without enlarging selected regions, and adding OCR of these regions to page images outperforms either input alone. We implement both as Loud and Clear (LoC), which combines higher-resolution pages with OCR from query-relevant regions without ground-truth annotations or additional training. LoC outperforms eight prior methods on SciEGQA, ViDoRe-v3, and MMLongBench-Doc, improving over the strongest, ColQwen3, by 8.88, 3.09, and 4.22 points with the same retriever and generator. It also outperforms its page-only variant under the same visual token budget. These results locate a bottleneck beyond retrieval: how the retrieved pages are given to the generator.
Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAG
Jiaqi Wei, Wenxuan Huang, Chengdong Xu, Xiang Zhang, Wanli Ouyang
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 evaluations conflate these two causes. We study how much apparent retrieval failure is instead caused by search drift: the search no longer tracks an unanswered sub-question. Holding the retriever, corpus, and generation model fixed, we introduce ExecutionRAG, a training-free requirement register that records open sub-questions and their supporting evidence. The register changes search guidance but not evidence access, so each gold passage it recovers certifies that the passage was reachable by the original retriever. On 1,000 MuSiQue questions, the number of wrong answers with unretrieved required evidence falls from 382 to 234 with all-MiniLM-L6-v2 and from 383 to 274 with Qwen3-Embedding-0.6B. These counts correspond to 69% to 44% and 66% to 48% of each system's wrong answers, respectively. Crucially, evidence recovery does not produce a proportional reduction in total error: premature resolutions and abstentions increase as missing-evidence failures decrease. The central finding is therefore a shift in the remaining bottleneck, from guiding search toward required evidence to verifying that the retrieved evidence is sufficient.
Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks
Fazle Mohammed Tasfiq, Sabab Attin, Sheikh Md. Tahmid Hossain, Raiat Reza, Tanzim Ahmmed, Nafis Chowdhury, Anika Ahmed, Moinul Haque, Farig…
Retrieval-Augmented Generation (RAG) models have become almost a cornerstone of open-domain question answering tasks; in which the quality of answers generated in the process, greatly relies on the effectiveness of retrieval mechanisms. In the realm of LLM, the last two years have seen tremendous progress in RAG architectures, with many models reporting to have improved performance through various design innovations. The cultural question and answering systems of South Asia, in particular, present a specific challenge since the region is home to the vast number of languages and traditions, which are closely interrelated. Along with these deeply intertwined historical narratives increase the need for culturally grounded and context-aware interpretation. Despite major architectural advances in LLMs, claiming significant improvements, challenges remain when answering these region specific questions in native languages. In this study, we aim to extract high-performing factors to guide the development of optimized hybrid RAG systems. We further explore whether the integration of RAG changes performance differently for culturally grounded and non-cultural questions in a South Asian multilingual setup, and whether RAG produces a higher overall percentage of correct answers than contexted answering. We also examine how LLM performance changes when RAG methods are integrated into the question-answering pipeline in comparison with non-contexted and contexted answering and, evaluate whether the introduction of RAG benefits popular or non-popular culturally grounded questions more. Not only does our work evaluate the current methods but also carves a path for future designs of more accurate and efficient question-answering pipelines.
GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generation
Yining Tang, Junyu Zhang, Haomiao Qiu, Yongchao Liu, Jiajun Zheng, Zhao Wang, Ziyue Qiao, Chao Wu
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 introduce GraphRAG-LTM, a Layered Threat Modeling framework that tests three nested levels of attacker access. BB Query uses ranking feedback to make query edits under a semantic-similarity constraint and demote relevant seed chunks. WB Query uses retriever gradients for the same objective. Graph-aware WB keeps the white-box adversarial query and deletes bridge triplets from the query-specific evidence graph, disrupting multi-hop evidence propagation through localized graph edits. Across datasets, retrievers, and LLM backbones, rank feedback alone reduces answer quality, gradient access strengthens query attacks, and bridge-triplet deletion further impairs supporting-fact retrieval. Further analyses show how seed retrieval and graph evidence jointly contribute to these failures.
Foundational papers
- 2020Retrieval-augmented generation for knowledge-intensive nlp tasks31,559 citations
- 2023
- 2023Active retrieval augmented generation1,856 citations
- 2024
- 2024
- 2024
- 2025
- 2026-10
Retrieval-augmented generation for knowledge-intensive nlp tasks
P Lewis, E Perez, A Piktus, F Petroni et al.
… generation models with a non-parametric memory through a general-purpose fine-tuning approach which we refer to as retrieval-augmented generation … both the generator and retriever …
Searching for best practices in retrieval-augmented generation
X Wang, Z Wang, X Gao, F Zhang, Y Wu et al.
… optimal practices for implementing retrieval-augmented generation in order to improve the … retrieval-augmented generation systems but also establish a foundation for future research. …
Retrieval-augmented generation for large language models: A survey
Y Gao, Y Xiong, X Gao, K Jia, J Pan, Y Bi, Y Dai et al.
… Retrieval-Augmented Generation (RAG) has emerged as a … This enhances the accuracy and credibility of the generation, … the retrieval, the generation and the augmentation techniques. …
Evaluation of retrieval-augmented generation: A survey
H Yu, A Gan, K Zhang, S Tong, Q Liu, Z Liu
… Retrieval-Augmented Generation (RAG) has recently gained … through external information retrieval. Evaluating these RAG … metrics of the Retrieval and Generation components, such as …
LightRAG: Simple and Fast Retrieval-Augmented Generation.
Z Guo, L Xia, Y Yu, T Ao, C Huang
… in LLMempowered Retrieval-Augmented Generation through the … retrieval. LightRAG utilizes a comprehensive knowledge graph to facilitate rapid and relevant document retrieval, …
Active retrieval augmented generation
Z Jiang, FF Xu, L Gao, Z Sun, Q Liu et al.
… gathering information throughout generation is essential. In … retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation. …
Retrieval-augmented generation for natural language processing: A survey
S Wu, Y Xiong, Y Cui, H Wu, C Chen, Y Yuan et al.
… of retrieval-augmented generation (RAG), which leverages an external knowledge base to augment … ), with a focus on retrievers and retrieval fusions. We introduce a novel taxonomy of …
Retrieval-augmented generation for ai-generated content: A survey
P Zhao, H Zhang, Q Yu, Z Wang, Y Geng, F Fu et al.
… to improve the generation process. There are several foundational paradigms (… how the retrieved results augment the generation: they can serve as augmented inputs to the generator […
Graph retrieval-augmented generation: A survey
B Peng, Y Zhu, Y Liu, X Bo, H Shi, C Hong et al.
… by integrating a retrieval component within the generation process. … (3) Lacking Global Information: RAG can only retrieve a … be used in the retrieval and generation stages: Graph Neural …
Parametric retrieval augmented generation
W Su, Y Tang, Q Ai, J Yan, C Wang, H Wang et al.
… retrieval augmented generation following a Retrieve-Update-Generate (RUG) workflow as shown in Figure 1. The Retrieve step … parametric representations of the retrieved documents to …
How this page is made. Foundational papers and citation counts come from academic search via the AISA Scholar API, with abstracts read from each paper’s page; recent preprints and monthly volumes come from the public arXiv API (metadata CC0). The digest is written by a language model from those abstracts only — every theme links the papers it draws on, and figures not in the inputs are removed.
Sources & citations
- Retrieval-augmented generation for knowledge-intensive nlp tasks 31,559 citations
- Searching for best practices in retrieval-augmented generation 418 citations
- Retrieval-augmented generation for large language models: A survey 8,576 citations
- Evaluation of retrieval-augmented generation: A survey 600 citations
- LightRAG: Simple and Fast Retrieval-Augmented Generation. 960 citations
- Active retrieval augmented generation 1,856 citations
- Retrieval-augmented generation for natural language processing: A survey 314 citations
- Retrieval-augmented generation for ai-generated content: A survey 1,127 citations
- Graph retrieval-augmented generation: A survey 950 citations
- Parametric retrieval augmented generation 110 citations
- Private Retrieval Augmented Generation via Random Projection arXiv · 2026-10-15
- Multi-sourced AI Tutor for Non-Native English Speaker Students arXiv · 2026-10-15
- CARA: Causally Guided Retrieval Agent for Question Answering arXiv · 2026-10-15
- TEM: Temporal State Tracking Memory for Large Language Model Agents arXiv · 2026-10-15
- Loud and Clear: Making Visual Evidence Count in Multimodal Document RAG arXiv · 2026-10-15
- Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAG arXiv · 2026-10-15
- Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks arXiv · 2026-10-14
- GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generation arXiv · 2026-10-14