AgentFlareScholar · retrieval augmented generation
Retrieval-Augmented Generation: Research Digest
10 foundational papers with 48,020 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
When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG
Zhouting 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-reranking baseline and a hybrid lexical--dense retriever. Rather than classifying baseline retrieval as simply successful or unsuccessful, we estimate the question-specific incremental evidence-retrieval benefit of hybrid retrieval using features available before the routing decision. A regularized linear model and decision threshold are selected using document-grouped cross-validation and frozen prior to held-out evaluation. On 60 previously unseen QASPER training-split articles (188 questions, 169 evidence-evaluable), the policy triggers hybrid retrieval on 46 questions (24.5\%) and obtains the same evidence Hit@10 as always-hybrid retrieval (78.70\%, versus 76.92\% for always-keep). Paired, paper-cluster bootstrap intervals do not establish a reliable utility advantage. We further compare generated answers from a 4-bit Qwen3-4B model under the three retrieval policies. Provisional answer-level assessments show no clear correctness or faithfulness improvement after partial review, despite the evidence-retrieval result. The generation assessments remain model-assisted and lack independent human validation. These results expose an important distinction between retrieving relevant evidence efficiently and improving the reliability of the generated answer. The work is presented as a reproducible empirical study, not a claim of statistically established answer-quality superiority.
Tessera: Structure-Completed Evidence Units for Web Retrieval-Augmented Generation
Peichun Hua, He Sun, Zirui Zhuang, Qi Qi, Yiming Qiu, Shinan Liu, Yunming Xiao
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 that this coupling loses evidence in text and screenshot pipelines alike: evidence present in the source page often fails to reach the reader intact, particularly structured content such as tables and infoboxes, which chunking separates from the headers and context that give it meaning. Stronger extraction, context expansion, and larger reader budgets leave the loss in place. We present Tessera, a training-free evidence delivery layer that decouples what a pipeline retrieves from what its reader reads. Given the pages behind any ranked list, Tessera rebuilds their HTML into fine-grained evidence units, each completed with its page title, section path, and table headers, selects the units relevant to the query, and packs them into the reader context at an unchanged token budget. The index, the retriever, and the reader stay as they are, so Tessera applies to text, screenshot, and agentic pipelines. Across three question answering benchmarks, Tessera improves answer accuracy by 5 to 6 points on text and screenshot pipelines, consistently across readers, retrievers, and reader budgets, and outperforms strong HTML-aware and structure-aware RAG baselines under matched budgets. The gains carry over to multi-step agentic search. Our code is publicly available at https://github.com/sarendis56/Tessera.
SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation
Zafer 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 dependencies, and provide incomplete evidence for multi-hop reasoning. We propose SpectRAG, a spectral graph-augmented retrieval framework that combines hybrid candidate seeding, weighted chunk graph construction, graph-based expansion, spectral relevance propagation, and token-budgeted context selection. Document chunks are represented by dense semantic embeddings and graph-spectral coordinates derived from a weighted chunk graph whose edges encode semantic similarity, document adjacency, section hierarchy, shared entities, citation links, and similarity between LLM-generated utility questions. At query time, SpectRAG builds a high-recall seed set using exact inner-product search and hybrid relevance signals, expands it over the chunk graph, re-scores candidates using graph proximity and spectral information, and assembles the final context under a fixed token budget. The goal is not merely to retrieve individually similar chunks, but to construct a context that is relevant, diverse, structurally connected, and sufficient for grounded reasoning. Experiments on MultiHopRAG, UltraDomain, and long-document question-answering settings show that SpectRAG improves broad evidence recovery and achieves competitive generation quality against dense, hybrid, HyDE, LightRAG, and NaiveRAG baselines. The results further indicate that graph-spectral structure is particularly useful for inference-oriented and cross-document retrieval, while highlighting trade-offs in early precision, computational cost, and domain-dependent performance.
Governed Sovereign RAG for Public Administration: Tripartite Epistemic Routing, Facet-Guided Clarification, and Deterministic Numeric Verification in Citizen Services
Andres Cruz Degante
Deploying conversational assistants at government service desks faces a tension between regulatory certainty (zero tolerance for invented fees), data sovereignty prohibiting commercial clouds, and high rates of underspecified or out-of-jurisdiction citizen queries. We present and evaluate a governed, sovereign Retrieval-Augmented Generation (RAG) architecture deployed on the official portal of the State of Tlaxcala, Mexico (tlaxcaladigital.gob.mx), covering 1,143 procedures and a decoupled directory of 924 offices. The system governs interactions via three pillars: (1) a two-stage tripartite epistemic gate (clarify_policy and a Boltzmann distribution over AnyJev) arbitrating among answering (SPECIFIC), facet-guided clarification (CLARIFY), and abstaining (ABSTAIN); (2) a post-generation deterministic numeric verifier (verify_numeric_guardrail) with SHA-256 cache invalidation ensuring every generated fee or validity figure belongs to the retrieved official record; and (3) an empirical evaluation across 380 organic production traces (8 weeks) and a 200-query stratified benchmark (5-fold CV: 86.41% +/- 7.50%). In production, 89.47% of traffic is resolved at Level 0 via deterministic templates without free generation (global p50 = 0.665 s; direct L0 p50 = 0.445 s; slow-tail p95 = 30.412 s under CPU queuing), with 0/40 fiscal amount hallucinations observed in Level 1 (95% bound <= 8.81%). On the benchmark, the system achieves 86.50% strict Top-1 accuracy (+10.00 pp over a binary neural gate, p = 0.00453, p_Holm = 0.01172), pairing a 93.00% conditional safe upper bound with a 70.87% dropout-adjusted effective resolution after accounting for 53.33% citizen drop-off in clarification menus.
QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG
Yifan Zhao, Qianyang Zhao, Xinyu Guan, kai wei, Yuming Deng
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. QESChunker constructs document-specific chunk indices by optimizing over human-annotated or LLM-generated question--evidence pairs, without access to held-out test queries. We formulate non-overlapping and overlapping index construction through a unified question--evidence utility-maximization objective, turning chunking into a supervised combinatorial optimization problem. Under the non-overlap constraint, the objective decomposes over chunks and can be optimized exactly in polynomial time by dynamic programming. When overlap is allowed, the objective becomes monotone submodular; exact optimization is NP-hard, but our greedy achieves a (1-1/√e)-approximation. Across two self-constructed and three public datasets, both variants outperform existing chunking methods in complete-evidence recall in nearly all evaluated settings, under the same overlap regime and a fixed hybrid retriever. These results recast chunking as supervised, budget-aware index construction for evidence retrieval.
RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG
Zekai Chen, Hao Zhu, Yu Liu, Xunkai Li, Zejian Kang, Rui Qian, Quanjiang Li, Rong-Hua Li
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 always necessary, introducing additional computation and potentially incorrect answers. Our empirical analysis reveals that Agentic execution provides query-dependent benefits, while additional operations may improve, preserve, or degrade answer accuracy. These findings motivate controlling both Agent invocation and subsequent execution. To address these challenges, we propose RouteDRAG, a learning-based framework comprising four components. Unified Document Index organizes multimodal content into a graph-backed index and derives query representations from initial retrieval. Adaptive Path Routing preserves exact answering and predicts the relative benefit of Agent over shorter execution paths. Dynamic Agent Execution maintains an evolving workspace and refines Planner proposals to control tool use and termination. Sequential Policy Learning first trains operation control from observed outcomes and then trains path routing using the resulting Agent's performance. Across two benchmarks, RouteDRAG achieves an average accuracy improvement of 3.47 percentage points over shorter-path-only execution while assigning only 79.3% of queries to Agent. Notably, it also surpasses uniform Agent execution on both benchmarks while requiring fewer answering calls. Our code is now available at https://github.com/Ereshkigal1/RouteDRAG.
LM-DSB: A Lightweight Multi-agent System for Automated Daily Safety Bulletin Generation in Construction
Xianxiang Zhao, Advik Mehta, Falak Sethi, Brian Gue, Qipei Mei, Lingzi Wu
Construction safety management still struggles to produce daily safety bulletins (DSBs), structured daily communications that identify site-specific hazards, convey safety protocols, and set preventive measures for workers. Manual DSB creation takes 2-3 hours daily and yields inconsistent quality, with 25% of crews never conducting pretask planning (Olson et al., 2016), diverting safety personnel from field supervision. This study proposes the Lightweight Multi-Agent DSB System (LM-DSB), which integrates retrieval-augmented generation (RAG) with a locally deployable Large Language Model (LLM) to automate DSB generation on consumer-grade personal computers. LM-DSB coordinates specialized planner, researcher, and writer agents in a hierarchical architecture, enhanced by domain-specific fine-tuning on construction safety documentation and RAG grounding in 37 health, safety, and environment (HSE) documents. A two-phase validation assessed feasibility. Phase 1 comparative evaluation showed the multi-agent RAG system (Llama 3-8B) outperformed all alternative configurations, with strong lexical alignment and coherence (TF-IDF: 0.70, BLEU: 0.39, ROUGE-1: 0.66) and near-complete document generation (length ratio: 1.01 vs. 0.39 for single-agent RAG). Phase 2 expert evaluation (N=40) confirmed practical acceptability (mean scores 3.50-4.20 on a 5-point scale), particularly in regulatory compliance (4.20) and factual accuracy (4.10). The findings show that architectural design enables lightweight models to handle safety-critical documentation on consumer-grade hardware, advancing technology democratization in construction safety management. Limitations include knowledge base scope, language constraints, and lack of field deployment validation; future work should address multimodal integration and workflow adoption.
OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning
Hui Yang, Jiaoyan Chen, Yongsheng Gao
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 incorporating external information, but often overlooks logical relationships and relies heavily on the LLM's own reasoning, which can compromise answer faithfulness. We propose OA-RAG, an agent that integrates formal reasoning with LLM reasoning, drawing on both the logical structure and informal annotations of domain ontologies. For each answer, OA-RAG reports the ontology observations used as evidence and a model-assessed grounding level (entailed, supported, related, or unrelated) that characterises the strength of that evidence. Across benchmarks derived from three large-scale ontologies and six real-world medical question-answering tasks, OA-RAG achieves the best overall performance among the evaluated ontology-fine-tuned and popular RAG methods, with particularly strong results on reasoning-intensive tasks. The reported grounding levels also offer a useful indication of answer reliability, with stronger grounding generally associated with higher accuracy. Finally, our results demonstrate the value of ontologies as knowledge sources: OA-RAG is competitive with, and sometimes outperforms, domain-specific RAG systems that draw on sources such as textbooks.
Foundational papers
- 2020Retrieval-augmented generation for knowledge-intensive nlp tasks32,682 citations
- 2023
- 2023Active retrieval augmented generation1,915 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 32,682 citations
- Searching for best practices in retrieval-augmented generation 427 citations
- Retrieval-augmented generation for large language models: A survey 8,804 citations
- Evaluation of retrieval-augmented generation: A survey 618 citations
- LightRAG: Simple and Fast Retrieval-Augmented Generation. 999 citations
- Active retrieval augmented generation 1,915 citations
- Retrieval-augmented generation for natural language processing: A survey 329 citations
- Retrieval-augmented generation for ai-generated content: A survey 1,153 citations
- Graph retrieval-augmented generation: A survey 981 citations
- Parametric retrieval augmented generation 112 citations
- When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG arXiv · 2026-10-27
- Tessera: Structure-Completed Evidence Units for Web Retrieval-Augmented Generation arXiv · 2026-10-27
- SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation arXiv · 2026-10-27
- Governed Sovereign RAG for Public Administration: Tripartite Epistemic Routing, Facet-Guided Clarification, and Deterministic Numeric Verification in Citizen Services arXiv · 2026-10-27
- QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG arXiv · 2026-10-27
- RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG arXiv · 2026-10-27
- LM-DSB: A Lightweight Multi-agent System for Automated Daily Safety Bulletin Generation in Construction arXiv · 2026-10-27
- OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning arXiv · 2026-10-26