Search arXiv⌕ Search

method

Retrieval-augmented generation

Retrieval-augmented generation: explore 136 source-linked works published from 2026 to 2026, with original documents and citations.

Search within this collectionFollow this collection with RSS

Coverage and selection

Includes records with this source-supplied label or an explicit phrase match in their metadata. Matches indicate a mention, not proof that a paper uses a method or tests a material. Source versions are consolidated by DOI.

Sources: arxiv. Collection updated 2026-09-16. Counts describe this index, not the complete source archives.

arXiv2026

EduGuard: A Safe RAG-Based LLM Tutor for Programming Education

Generative AI (GenAI) is increasingly used by students for programming explanation, debugging, and assignment support. Yet unrestricted large language model (LLM) tutors can hallucinate, contradict course policy, reveal complete solutions, and foster passive dependence. This paper presents EduGuard, a safe retrieval-augmented generation (RAG) tutoring framework for introductory programming. EduGuard integrates query understanding, instructor-approved course retrieval, pedagogical strategy selection, rubric-aware generation, claim-level verification, and overreliance control. To make evaluation provenance explicit, we construct BILearn-CS, a 600-query instructor-authored, TA-validated benchmark spanning concept questions, debugging cases, misconceptions, assignment-support requests, code-mixed Bangla-English queries, and adversarial direct-answer prompts. Moving beyond a synthetic-only benchmark, we further evaluate on a 150-query public CS50-style course-forum set and run a small controlled pilot with 10 undergraduates using a counterbalanced pre-test/post-test design. Using Meta-Llama-3.1-8B-Instruct as the primary generator, hybrid FAISS/BM25 retrieval, and DeBERTa-v3-large-MNLI as an architecturally separate verifier, EduGuard is compared against strong baselines: GPT-4o-mini Tutor, Llama Socratic Tutor, LPITutor-style RAG, RAG with rubric prompting, and RAG with same-model self-checking. On BILearn-CS, EduGuard attains the best correctness (90.1%), grounding (89.4%), and rubric alignment (90.8%), with the lowest hallucination (4.9%) and direct-answer leakage (9.8%). In the pilot, it raises immediate post-test accuracy from 68.4% to 81.2% and cuts overreliance from 38.0% to 17.0% relative to GPT-4o-mini Tutor. These results suggest safe GenAI tutoring requires not only retrieval or strong prompting, but explicit pedagogical control, evidence verification, and deployment safeguards.

cs.CY↗
arXiv2026

InsightToast: Proactive Information Retrieval & Glanceable Visualization in the Side Channel of Data-Rich Meetings

Missing institutional context during meetings can impede effective participation. Retrieving relevant information, often scattered across heterogeneous internal and external sources, requires costly task-switching that disrupts both individual focus and collective conversational flow, particularly detrimental during cognitively demanding tasks such as decision-making. We introduce InsightToast, a mixed-initiative application that monitors verbal discourse in real time, identifies topics and informational needs as they emerge, and proactively retrieves relevant information through a multi-agent large language model (LLM)-based pipeline integrating retrieval-augmented generation (RAG) to produce source-grounded insights as succinct text and glanceable interactive charts, delivered through a peripheral interface as ephemeral toasts in the conversation's side channel. To demonstrate the potential for yielding serendipitous insights, we showcase a usage scenario involving a knowledge base of legislative documents as the meeting's context. We then report on a comparative study (N=16), in which participants arrived at informed policy decisions while maintaining natural conversation flow.

cs.HC↗
arXiv2026

PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning

We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language models (LLMs) and large vision-language models (LVLMs). PetQA contains 10,076 text-only and 8,751 multimodal QA pairs derived from real-world questions about dogs and cats, paired with answers from expert veterinarians. Its test split, PetQA-Bench, further includes annotations for question types and clinical conditions. We evaluate eighteen models using ROUGE, BERTScore, and LLM-as-a-judge metrics for factuality and helpfulness under three settings: zero-shot inference, retrieval-augmented generation (RAG), and supervised fine-tuning (SFT). The benchmarking results provide an overview of the strengths and limitations of current models in addressing veterinary clinical queries and highlight the need for more effective adaptation methods to develop clinically reliable AI systems for veterinary care. To facilitate broader use, we additionally provide translated versions of PetQA-Bench in five languages.

cs.CL↗
arXiv2026

CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation

Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individually relevant yet collectively incoherent. We introduce Coherence-Aware Graph Encoding (CAGE), a reranking framework that models "between-chunk coherence" across four dimensions: Intra-Domain Relevance, Noise Resistance, Informational Bonding, and Factual Consistency. Our pipeline transforms retrieved passages into directed heterogeneous entity graphs, amplifies factual anchors via min-out-degree reweighting, encodes structural patterns through a Relational Graph Convolutional Network, and fuses inter-chunk coherence with query relevance for final ranking. Evaluated across four multi-hop benchmarks, CAGE matches or outperforms strong baselines including monoT5 in Recall@5 on bridge-dominated datasets and consistently improves downstream Exact Match, demonstrating that structurally coherent context yields more precise answers even when retrieval recall is comparable or lower.

cs.CL↗
arXiv2026

Shadow Queries for Private Retrieval in Vector Databases

Large language models (LLMs) increasingly rely on information retrieval (IR) systems, such as Retrieval-Augmented Generation (RAG), to incorporate domain-specific knowledge without costly re-training. These systems often store pre-computed document embeddings in cloud-based vector databases. However, such embeddings are vulnerable to embedding inversion attacks (EIAs), which can reconstruct their underlying text. Existing defenses, such as adding noise or scaling embeddings, often provide limited privacy or significantly reduce retrieval utility. We propose SHAQ (shadow query generation), a semantic-decomposition and embedding-decoupling defense against EIAs. SHAQ is based on the insight that EIAs rely on the strong coupling between an embedding and its original text. Instead of storing document embeddings directly, SHAQ uses a generative language model to create diverse shadow queries that capture different semantic aspects of each document. These queries are then encoded and stored in place of the original document embeddings, thereby decomposing document semantics and decoupling stored embeddings from the source text. Experiments across diverse IR datasets show that SHAQ substantially improves privacy while preserving retrieval utility, achieving a recovery rate as low as 0.2104, defending up to 19.50% more tokens than baseline defenses, and reaching up to 0.7967 MAP@10 with up to 5.53% utility improvement. These results demonstrate that semantic decomposition and embedding decoupling provide an effective alternative to directly modifying embeddings for defending against EIAs.

cs.AI↗
arXiv2026

Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval

Dense retrieval systems are core components of modern search engines, recommendation platforms, and retrieval-augmented generation pipelines. They encode documents and queries into dense embeddings, enabling efficient semantic search via vector similarity. However, because document embeddings are computed offline and stored in static indexes, these systems struggle to adapt to user feedback or evolving search intent. To address this limitation, we introduce \emph{embedding surgery}, a lightweight approach for adaptive ranking correction in dense retrieval. The method applies localized, minimal updates to selected document embeddings at query time, guided by editorial feedback, user interactions, or pseudo-labels from large language models. We formulate embedding surgery as a convex optimization problem that enforces ranking constraints while minimizing modifications to the affected document representations. We integrate embedding surgery into standard dense retrieval pipelines and evaluate it on TREC Deep Learning, TREC Robust, TREC CAsT, and MS MARCO benchmarks. Results show consistent improvements (e.g., up to +60.64\% relative improvement in nDCG@10 on DL-Hard under editorial feedback), even under noisy or shifting feedback, with low computational cost and without disrupting the global structure of the embedding space. Extensive experiments show that ranking corrections propagate to semantically related queries and that embedding updates can be applied safely and efficiently to scalable Approximate Nearest Neighbor indexes via simple in-place overwriting, without requiring costly index reconstruction. Finally, embedding surgery complements query adaptation methods such as CoRocchio, yielding additional gains while being more robust to noisy feedback.

cs.IR↗
arXiv2026

Beyond Maintenance Manual Multimodal RAG: Suggesting What Tool

Aircraft technicians are required to consult the maintenance manual (MM) for nearly every task, and locating the relevant procedure across hundreds of pages remains time-consuming. Multimodal retrieval augmented generation (MRAG) has been proposed to address this, allowing technicians to retrieve procedures, together with the accompanying figures, through natural-language queries. However, retrieval alone does not tell the technicians which tools the task requires. The MM identifies special tools only when the corresponding step is reached, and it does not state hand tool requirements at all; to select hand tools, technicians are required to find the hardware dimension from the illustrated parts catalog (IPC) and infer the right tool from it. We therefore propose MRAG-SWAT, an extension of the MRAG pipeline that returns the required hand tools and special tools alongside the retrieved procedure. The framework was implemented for the Lycoming IO-360-N1A engine and demonstrated on eight test queries. By presenting the correct tools together with the procedure, MRAG-SWAT may help reduce repeated trips to the tool crib, prevent damage to aircraft caused by improper tool selection, and thereby avoid additional maintenance tasks and support continued airworthiness.

cs.ET↗
arXiv2026

NS-ST-GraphRAG: Neuro-Symbolic Spatio-Temporal GraphRAG for Literary Knowledge Processing

Long-form literary narratives pose a distinctive information-processing challenge for retrieval-augmented generation: relevant evidence is distributed across chapters, relations evolve over narrative time, and correct answers may depend jointly on temporal, spatial, and relational constraints. We propose NS-ST-GraphRAG, a neuro-symbolic spatio-temporal GraphRAG framework that integrates ontology-guided extraction, deterministic constraint checking, dual temporal coordinates, spatial scene attributes, and dynamic sub-graph retrieval. Instead of retrieving from a single corpus-level graph, the framework selects the graph state valid for the temporal and spatial scope of a query and grounds generated answers in traceable evidence. We further introduce Red-Chamber-QA, to our knowledge the first open multi-hop question-answering benchmark for classical Chinese literature, with time-, space-, and general-question categories, per-part evidence spans, and deterministic shortcut controls. On a 120-question held-out split, NS-ST-GraphRAG achieves mechanical answer reproduction of 0.733 versus 0.675 for the frozen window baseline and 0.083 for a closed-book model (McNemar exact p = 0.092, directionally favorable but not significant); semantic-judge accuracy is 0.866 versus 0.850. The pre-specified constrained-category condition of H2 is not supported by the delivered comparison. These results show how temporal graph representation, constrained extraction, and auditable evaluation integrate into a unified framework for verifiable knowledge processing over long-form narrative.

cs.CL↗
arXiv2026

Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

Retrieval-Augmented Generation (RAG) improves knowledge-intensive generation by conditioning language models on retrieved documents, but processing these documents becomes increasingly expensive as retrieval depth grows. Soft context compression reduces this cost by encoding documents into compact continuous representations that can be precomputed and reused across queries. However, many existing methods train compressed models by distilling from a full-context teacher. When the teacher is wrong, such distillation can reinforce its errors, while teacher imitation provides no direct signal for improving beyond the teacher. We propose DEX-Comp, a two-stage training recipe that separates reliable imitation from targeted exploration. Pure Distillation learns only from teacher-correct questions to mitigate error propagation, while Hard Exploration applies outcome-based reinforcement learning to teacher-failed questions to directly optimize answer correctness. Across five open-domain QA benchmarks and retrieval depths from top-$5$ to top-$30$, DEX-Comp at $16\times$ compression outperforms all evaluated compression baselines and surpasses the untuned full-context RAG model in average accuracy, while reducing time-to-first-token by $4.4\times$--$23.7\times$. Evaluations across additional datasets and backbones further demonstrate its generalization.

cs.CL↗
arXiv2026

Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability

Model upgrades are routine; memory migrations are not. An agent can keep the same memory store and still forget: a new model may interpret old notes differently, mixed embedding versions may break retrieval, and repair may fail without the original evidence. We compare memory as the same history is preserved verbatim for long-context reading (LC-RAW), divided into chunks for retrieval-augmented generation (RAG), compressed by a model into natural-language notes (NOTES), or normalized into a fixed-schema knowledge graph (KG-fixed). The study uses 48 synthetic histories with randomized answer codes, exact scoring, and two open-weight models with sub 10 billion parameters. Our measurements show that fixed-schema structures transfer reliably, with KG-fixed accuracy changing by only $+0.0004 \pm 0.0020$ following a writer swap. Conversely, compressed NOTES exhibit high model coupling, with accuracy shifting asymmetrically by $+9.91$ or $-13.28$ percentage points depending on the specific migration direction. In RAG systems, partial embedding migrations using a 50/50 mixed index capture only a 4.96-point accuracy improvement, forfeiting the majority of the 11.90-point gain achieved through full re-embedding. Diagnostic decomposition attributes 80% ($0.467 \pm 0.014$) of the NOTES accuracy deficit to information lost during initial construction, whereas retrieval failures drive 81% ($0.364 \pm 0.012$) of the RAG deficit. Finally, store-only repair of NOTES fails to reach a 90% performance recovery target in all 48 test cases, whereas retaining the raw source history enables successful recovery in 34 of 48 cases for one tested direction. These findings highlight the necessity of direction-specific migration testing, strict embedding space isolation, and the retention of source histories for memory repair.

cs.AI↗
arXiv2026

RAGMark: A Comprehensive Framework for Benchmarking Retrieval-Augmented Generation Systems

We present RAGMark, a modular benchmarking framework for advanced Retrieval-Augmented Generation (RAG) systems targeting small-scale multi-GPU environments. RAGMark evaluates diverse RAG components, including retrievers, vector databases, prompt-processing methods, and generator models, while collecting detailed per-stage metrics such as latency, GPU utilization, memory consumption, power usage, time to first token (TTFT), throughput, and answer quality. The framework is highly extensible, separating RAG stages, timing, and resource monitoring into modular components, and is designed to efficiently sweep large configuration spaces while minimizing repeated model and database initialization overhead. Using RAGMark, we characterize five RAG workloads on open-domain QA datasets across varying retrieval depths, model scales, reranking, compression methods, and vector database configurations. We show that while autoregressive generation dominates latency in naive pipelines, context-reduction techniques shift bottlenecks across compute, memory bandwidth, and preprocessing stages. Reranking and compression produce compounding benefits: reranking reduces compression workload itself, while both jointly reduce prefill and KV-cache traversal costs, lowering energy consumption by up to 66%. We further observe strong cross-stage interactions, where small upstream context reductions cascade through downstream latency, memory traffic, and energy consumption. The RAGMark source code is publicly available at: https://github.com/zferic/RAGMark.

cs.PF↗
arXiv2026

TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems

In the pursuit of enhancing domain-specific Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) emerges as a promising solution to mitigate issues such as hallucinations, outdated knowledge, and limited expertise in highly specialized queries. However, existing approaches to RAG fall short by neglecting system state variables, which are crucial for ensuring adaptive control, retrieval halting, and system convergence. In this paper, we introduce the TC-RAG through rigorous proof, a novel framework that addresses these challenges by incorporating a Turing Complete System to manage state variables, thereby enabling more efficient and accurate knowledge retrieval. By leveraging a memory stack system with adaptive retrieval, reasoning, and planning capabilities, TC-RAG not only ensures the controlled halting of retrieval processes but also mitigates the accumulation of erroneous knowledge via Push and Pop actions. In the case study of the medical domain, our extensive experiments on real-world healthcare datasets demonstrate the superiority of TC-RAG over existing methods in accuracy by over 7.20\%. Our dataset and code have been available at https://github.com/Artessay/TC-RAG .

cs.IR↗
arXiv2026

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG

Large language models (LLMs) have transformed natural language processing (NLP), enabling diverse applications by integrating large-scale pre-trained knowledge. However, their static knowledge limits dynamic reasoning over external information, especially in knowledge-intensive domains. Retrieval-Augmented Generation (RAG) addresses this challenge by combining retrieval mechanisms with generative modeling to improve contextual understanding. Traditional RAG systems suffer from disrupted contextual integrity due to text chunking and over-reliance on semantic similarity for retrieval, often resulting in shallow and less accurate responses. We propose Causal-Counterfactual RAG, a novel framework that integrates explicit causal graphs representing cause-effect relationships into the retrieval process and incorporates counterfactual reasoning grounded on the causal structure. Unlike conventional methods, our framework evaluates not only direct causal evidence but also the counterfactuality of associated causes, combining results from both to generate more robust, accurate, and interpretable answers. By leveraging causal pathways and associated hypothetical scenarios, Causal-Counterfactual RAG preserves contextual coherence, reduces hallucination, and enhances reasoning fidelity.

cs.CL↗
arXiv2026

Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models

Long-term memory (LTM) is fundamental to large language model (LLM)-based agents in the emerging Internet of Agents (IoA), where distributed multi-agent systems (DMAS) span cloud and edge networks. Existing evaluations are typically published by framework providers and focus on token usage and latency, rarely accounting for system-level cost or deployment in DMAS. These gaps are addressed with an independent reproducible testbed that evaluates accuracy, latency, CPU time, peak RAM, disk I/O and network usage in a simulated cloud-edge environment. Three venture capital-funded frameworks spanning vector, graph, and hybrid architectures, namely mem0, Graphiti, and cognee, are compared alongside retrieval-augmented generation (RAG) and full-context baselines on the LoCoMo benchmark under unconstrained and constrained network scenarios. Two clusters emerge: mem0, RAG, and full-context reach 77% to 81% accuracy, while Graphiti and cognee reach only 55% to 56%, a gap driven by retrieval incompleteness rather than reasoning failure. The RAG baseline matches the upper cluster at 8.4 times lower total cost of ownership (TCO) than mem0, and both are the only non-dominated backends on the Pareto frontier. Latency and bandwidth constraints as well as jitter leave retrieval quality unchanged for every backend, while vector-based LTM incurs a modest latency penalty of 4% to 5% under edge-cloud constraints. Compression precision rather than context volume determines LTM accuracy, as full-context forwarding underperforms mem0 despite supplying the entire conversation for each question.

cs.IR↗
arXiv2026

A Visionary Look at Vibe Researching

Vibe researching is an emerging paradigm in which human researchers provide high-level direction and critical judgment while LLM-based agents handle the labor-intensive execution of literature review, experimentation, data analysis, and manuscript drafting. Inspired by the "vibe coding" movement in software engineering, it occupies a middle ground between traditional manual research and fully autonomous AI research systems. This paper defines the concept, describes its methodology (multi-agent architectures, memory, tool use, retrieval-augmented generation, and the human's role as orchestrator), identifies seven technical limitations, weighs its positive and negative societal impacts, and maps each problem to a concrete future direction. Our goal is to provide the research community with a clear and honest map of the territory so that the conversation about responsible adoption can start from shared ground.

cs.CY↗
arXiv2026

PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents

Conversational and tool-using LLM agents operate over a context window that fills from several directions simultaneously. As a session proceeds, the agent accumulates user and assistant turns, entries drawn from a persistent memory store, and often largest of all, the verbatim outputs of tool calls such as file reads, search results, and API responses. Once the cumulative context exceeds the model's token budget, the framework must decide what to keep. The prevailing mechanism is recency truncation, sometimes paired with periodic summarization. This is topic-blind: a fact established early in a session is discarded simply because it is old, even when the current user query is about exactly that fact; conversely, verbose but irrelevant recent material is retained. Agents that must recall information across many turns, the defining case for memory, are precisely where recency truncation fails. Existing alternatives sit outside the agent's assembly step. Retrieval augmented generation fetches external documents into the prompt but does not arbitrate the agent's \emph{already-present} pooled context. Context-compression methods reduce token count by rewriting or pruning text, but operate query-blind and lossily. Neither treats memory entries, conversation turns, and tool outputs as a single candidate pool to be selected from by relevance at the moment the prompt is assembled.

cs.IR↗
arXiv2026

Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity

Vision Language Models have achieved near-human performance on single-document Visual Question Answering, yet their effectiveness degrades significantly when retrieving information from large collections of visually homogeneous documents. Existing multi-document benchmarks aggregate diverse document types, creating artificial separation in embedding space that does not reflect enterprise document repositories where thousands of records share identical visual templates. We identify this as embedding collapse and introduce Invoice Haystack, a benchmark with 1,500 anonymized invoice images paired with 200 discriminative question-answer pairs, specifically designed to stress-test retrieval under strong visual homogeneity. Invoice Haystack exhibits a mean pairwise cosine similarity of 0.73, compared to 0.38 (DocHaystack) and 0.31 (InfoHaystack) in existing benchmarks, posing a fundamentally more challenging retrieval problem. Addressing the identified challenge, we propose VL-RAG, a hybrid retrieval-augmented generation framework that jointly leverages text and visual embeddings to harness the complementary strengths of both modalities, followed by a VLM-based verification filter for precise document identification. VL-RAG achieves 60.0\% Recall@1 on Invoice Haystack-500, outperforming existing state-of-the-art method by up to an absolute 13.5 percentage points. It further improves retrieval considerably on DocHaystack-1000 (77.1\% vs.\ 75.2\%) and InfoHaystack-1000 (84.5\% vs.\ 80.0\%), establishing the proposed dual-stream fusion as a consistently superior retrieval strategy across both homogeneous and heterogeneous document collections.

cs.CV↗
arXiv2026

ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering

Document Visual Question Answering (DocVQA) often leverages Retrieval-Augmented Generation (RAG), where late-interaction encoders are commonly used to identify document pages relevant to a user query, before answer generation by a Large Vision-Language Model (LVLM). Existing approaches typically retrieve a fixed top-$k$ number of pages regardless of query complexity, which increases LVLM latency and may degrade answer accuracy. We introduce ViSAR (Visual Semantic Activation Retrieval), a training-free adaptive-$k$ retrieval method for late-interaction visual document retrieval. ViSAR operates directly in the embedding space to construct a query-conditioned page-level similarity matrix that highlights query-relevant semantics and dynamically determines the number of pages to retrieve. Across multiple encoders and LVLMs, ViSAR retrieves compact, query-adapted page sets that reduce RAG latency by up to 58.7\%, while maintaining or improving answer accuracy compared with fixed top-$k$ and adaptive retrieval heuristics. Furthermore, we show that the similarity matrix structure correlates with answer accuracy, suggesting future directions for retrieval quality-aware document understanding.

cs.IR↗
Compare source metadata on this page
WorkPublishedSource identifierSource
EduGuard: A Safe RAG-Based LLM Tutor for Programming Education2026-09-042607.15738arxiv
InsightToast: Proactive Information Retrieval & Glanceable Visualization in the Side Channel of Data-Rich Meetings2026-09-042608.31115arxiv
PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning2026-09-042609.04598arxiv
CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation2026-09-042609.04647arxiv
Shadow Queries for Private Retrieval in Vector Databases2026-09-042609.04767arxiv
Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval2026-09-042609.05110arxiv
Beyond Maintenance Manual Multimodal RAG: Suggesting What Tool2026-09-042609.05116arxiv
NS-ST-GraphRAG: Neuro-Symbolic Spatio-Temporal GraphRAG for Literary Knowledge Processing2026-09-042609.05139arxiv
Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG2026-09-282609.05152arxiv
Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability2026-09-042609.05339arxiv
RAGMark: A Comprehensive Framework for Benchmarking Retrieval-Augmented Generation Systems2026-09-042609.05760arxiv
TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems2026-09-032408.09199arxiv
Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG2026-09-032509.14435arxiv
Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models2026-09-032601.07978arxiv
A Visionary Look at Vibe Researching2026-09-032604.00945arxiv
PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents2026-09-032606.20047arxiv
Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity2026-09-032606.25343arxiv
ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering2026-09-032609.02486arxiv

These are bibliographic comparisons, not experimental rankings. Follow the original document for methods and conditions.