{"total":117,"rows":[{"id":"2507.05257","title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","created":"2025-07-07","cited_by_count":254,"area":"agents"},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83,"area":"rag"},{"id":"2407.13193","title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","created":"2024-07-18","cited_by_count":71,"area":"rag"},{"id":"2501.03468","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","created":"2025-01-07","cited_by_count":51,"area":"rag"},{"id":"2504.00125","title":"LLMs for Explainable AI: A Comprehensive Survey","created":"2025-03-31","cited_by_count":45,"area":null},{"id":"2410.13070","title":"Is Semantic Chunking Worth the Computational Cost?","created":"2024-10-16","cited_by_count":43,"area":"rag"},{"id":"2502.01113","title":"GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation","created":"2025-02-03","cited_by_count":40,"area":"rag"},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2505.16037","title":"Causal LLM Routing: End-to-End Regret Minimization from Observational Data","created":"2025-05-21","cited_by_count":28,"area":null},{"id":"2602.18998","title":"Benchmark Test-Time Scaling of General LLM Agents","created":"2026-02-22","cited_by_count":26,"area":"lr"},{"id":"2510.09738","title":"Judge's Verdict: A Comprehensive Analysis of LLM Judge Capability Through Human Agreement","created":"2025-10-10","cited_by_count":25,"area":null},{"id":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2510.16724","title":"A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications","created":"2025-10-19","cited_by_count":22,"area":"rag"},{"id":"2504.14891","title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","created":"2025-04-21","cited_by_count":20,"area":"rag"},{"id":"2505.17471","title":"FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain","created":"2025-05-23","cited_by_count":16,"area":"rag"},{"id":"2602.02823","title":"R2-Router: A New Paradigm for LLM Routing with Reasoning","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2508.02276","title":"CellForge: Agentic Design of Virtual Cell Models","created":"2025-08-04","cited_by_count":13,"area":"agents"},{"id":"2509.02718","title":"Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving","created":"2025-09-02","cited_by_count":13,"area":"inference"},{"id":"2509.11552","title":"HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking","created":"2025-09-15","cited_by_count":12,"area":"rag"},{"id":"2603.00873","title":"MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains","created":"2026-03-01","cited_by_count":12,"area":"lr"},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2409.13694","title":"Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study","created":"2024-09-03","cited_by_count":8,"area":"rag"},{"id":"2502.18817","title":"Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models","created":"2025-02-26","cited_by_count":8,"area":"rag"},{"id":"2504.01509","title":"PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation","created":"2025-04-02","cited_by_count":8,"area":null},{"id":"2506.00789","title":"RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems","created":"2025-06-01","cited_by_count":8,"area":"rag"},{"id":"2602.02888","title":"HALT: Hallucination Assessment via Log-probs as Time series","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2603.07379","title":"SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions","created":"2026-03-07","cited_by_count":8,"area":"lr"},{"id":"2504.20119","title":"Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets","created":"2025-04-28","cited_by_count":7,"area":"rag"},{"id":"2604.14572","title":"Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG","created":"2026-04-16","cited_by_count":7,"area":"rag"},{"id":"2502.13465","title":"HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks","created":"2025-02-19","cited_by_count":6,"area":"rag"},{"id":"2505.21072","title":"Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation","created":"2025-05-27","cited_by_count":6,"area":"rag"},{"id":"2507.20930","title":"FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models","created":"2025-07-28","cited_by_count":6,"area":null},{"id":"2602.00296","title":"RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing","created":"2026-01-30","cited_by_count":6,"area":"rag"},{"id":"2505.10989","title":"DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization","created":"2025-05-16","cited_by_count":5,"area":"rag"},{"id":"2505.11180","title":"mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs","created":"2025-05-16","cited_by_count":5,"area":"rag"},{"id":"2508.03644","title":"Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?","created":"2025-08-05","cited_by_count":5,"area":"mllm"},{"id":"2603.19225","title":"FinTradeBench: A Financial Reasoning Benchmark for LLMs","created":"2026-03-19","cited_by_count":5,"area":"lr"},{"id":"2604.16966","title":"Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning","created":"2026-04-18","cited_by_count":5,"area":"agents"},{"id":"2606.30306","title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","created":"2026-06-29","cited_by_count":5,"area":null},{"id":"2505.13538","title":"RAGXplain: From Explainable Evaluation to Actionable Guidance of RAG Pipelines","created":"2025-05-18","cited_by_count":4,"area":"rag"},{"id":"2506.05766","title":"BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2510.11974","title":"CTIConnect: A Benchmark for Retrieval-Augmented LLMs over Heterogeneous Cyber Threat Intelligence","created":"2025-10-13","cited_by_count":4,"area":"rag"},{"id":"2410.13258","title":"How Does Knowledge Selection Help Retrieval Augmented Generation?","created":"2024-10-17","cited_by_count":3,"area":"rag"},{"id":"2507.18392","title":"CLEAR: Error Analysis via LLM-as-a-Judge Made Easy","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2602.21553","title":"Revisiting RAG Retrievers: An Information Theoretic Benchmark","created":"2026-02-25","cited_by_count":3,"area":"rag"},{"id":"2603.19281","title":"URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models","created":"2026-03-02","cited_by_count":3,"area":"rag"},{"id":"2412.05223","title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","created":"2024-12-06","cited_by_count":2,"area":null},{"id":"2502.19779","title":"Do Retrieval-Augmented Language Models Adapt to Varying User Needs?","created":"2025-02-27","cited_by_count":2,"area":"rag"},{"id":"2504.15689","title":"The Viability of Crowdsourcing for RAG Evaluation","created":"2025-04-22","cited_by_count":2,"area":"rag"},{"id":"2505.23299","title":"Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs","created":"2025-05-29","cited_by_count":2,"area":"rag"},{"id":"2507.22927","title":"PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation","created":"2025-07-23","cited_by_count":2,"area":"rag"},{"id":"2510.11956","title":"Investigating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries","created":"2025-10-13","cited_by_count":2,"area":"rag"},{"id":"2511.14531","title":"LiveRAG: A diverse Q&A dataset with varying difficulty level for RAG evaluation","created":"2025-11-18","cited_by_count":2,"area":"rag"},{"id":"2601.02917","title":"RAL2M: Retrieval Augmented Learning-To-Match Against Hallucination in Compliance-Guaranteed Service Systems","created":"2026-01-06","cited_by_count":2,"area":"rag"},{"id":"2601.12991","title":"RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systems","created":"2026-01-19","cited_by_count":2,"area":"rag"},{"id":"2604.01733","title":"From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents","created":"2026-04-02","cited_by_count":2,"area":"rag"},{"id":"2604.08304","title":"Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions","created":"2026-04-09","cited_by_count":2,"area":"rag"},{"id":"2604.09174","title":"Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG","created":"2026-04-10","cited_by_count":2,"area":"rag"},{"id":"2605.19341","title":"HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models","created":"2026-05-19","cited_by_count":2,"area":"wm"},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2502.13719","title":"TrustRAG: An Information Assistant with Retrieval Augmented Generation","created":"2025-02-19","cited_by_count":1,"area":"rag"},{"id":"2507.18857","title":"PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2508.20417","title":"KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval","created":"2025-08-28","cited_by_count":1,"area":"rag"},{"id":"2509.25184","title":"Incentive-Aligned Multi-Source LLM Summaries","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.21538","title":"InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation","created":"2025-10-24","cited_by_count":1,"area":"rag"},{"id":"2511.12520","title":"TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction","created":"2025-11-16","cited_by_count":1,"area":"lr"},{"id":"2601.16967","title":"Empowering Medical Equipment Sustainability in Low-Resource Settings: An AI-Powered Diagnostic and Support Platform for Biomedical Technicians","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.06526","title":"Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2602.07739","title":"HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation","created":"2026-02-08","cited_by_count":1,"area":"rag"},{"id":"2602.16942","title":"SourceBench: Can AI Answers Reference Quality Web Sources?","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2602.18583","title":"Luna-2: Scalable Single-Token Evaluation with Small Language Models","created":"2026-02-20","cited_by_count":1,"area":"safety"},{"id":"2603.10765","title":"RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems","created":"2026-03-11","cited_by_count":1,"area":"rag"},{"id":"2603.20299","title":"HCAG: Hierarchical Abstraction and Retrieval-Augmented Generation on Theoretical Repositories with LLMs","created":"2026-03-19","cited_by_count":1,"area":"rag"},{"id":"2604.01221","title":"HippoCamp: Benchmarking Contextual Agents on Personal Computers","created":"2026-04-01","cited_by_count":1,"area":"agents"},{"id":"2604.12047","title":"Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG","created":"2026-04-13","cited_by_count":1,"area":"rag"},{"id":"2604.12138","title":"Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions","created":"2026-04-13","cited_by_count":1,"area":"rag"},{"id":"2604.17943","title":"A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.18234","title":"Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.05244","title":"Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction","created":"2026-05-04","cited_by_count":1,"area":"rag"},{"id":"2605.21102","title":"ACL-Verbatim: hallucination-free question answering for research","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.27164","title":"Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering","created":"2026-05-26","cited_by_count":1,"area":"rag"},{"id":"2605.27494","title":"Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?","created":"2026-05-26","cited_by_count":1,"area":"rag"},{"id":"2606.04646","title":"QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.16817","title":"Understanding the Behaviors of Environment-aware Information Retrieval","created":"2026-06-15","cited_by_count":1,"area":"rag"},{"id":"2607.00725","title":"Recall Is Not Enough: A Reader-Context Diagnostic for Budget-Constrained Retrieval-Augmented Generation","created":"2026-07-01","cited_by_count":1,"area":"rag"},{"id":"2607.04223","title":"Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)","created":"2026-07-05","cited_by_count":1,"area":"rag"},{"id":"2607.06008","title":"PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows","created":"2026-07-07","cited_by_count":1,"area":"agents"},{"id":"2607.29402","title":"Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings","created":"2026-07-31","cited_by_count":1,"area":"rag"},{"id":"2504.12342","title":"CRAB: A Benchmark for Evaluating Curation of Retrieval-Augmented LLMs in Biomedicine","created":"2025-04-15","cited_by_count":0,"area":"rag"},{"id":"2506.02503","title":"KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG","created":"2025-06-03","cited_by_count":0,"area":"rag"},{"id":"2506.07940","title":"Gradients: When Markets Meet Fine-tuning -- A Distributed Approach to Model Optimisation","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2508.02074","title":"The SMeL Test: A simple benchmark for media literacy in language models","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2510.11897","title":"A Longitudinal Study on Different Annotator Feedback Loops in Complex RAG Tasks","created":"2025-10-13","cited_by_count":0,"area":"rag"},{"id":"2511.09831","title":"Answering Students' Questions on Course Forums Using Multiple Chain-of-Thought Reasoning and Finetuning RAG-Enabled LLM","created":"2025-11-13","cited_by_count":0,"area":"lr"},{"id":"2512.00367","title":"Breaking It Down: Domain-Aware Semantic Segmentation for Retrieval Augmented Generation","created":"2025-11-29","cited_by_count":0,"area":"rag"},{"id":"2601.08919","title":"LLMs as Assessors: Right for the Right Reason?","created":"2026-01-13","cited_by_count":0,"area":"lr"},{"id":"2602.04579","title":"AIANO: Enhancing Information Retrieval with AI-Augmented Annotation","created":"2026-02-04","cited_by_count":0,"area":"rag"},{"id":"2602.13890","title":"Evaluating Prompt Engineering Techniques for RAG in Small Language Models: A Multi-Hop QA Approach","created":"2026-02-14","cited_by_count":0,"area":"rag"},{"id":"2603.29875","title":"UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough","created":"2026-02-06","cited_by_count":0,"area":"rag"},{"id":"2605.00964","title":"Seeking Information with RAG-Assistants: Does Model Size Matter in Human-AI Collaborations?","created":"2026-05-01","cited_by_count":0,"area":null}],"next_cursor":"100"}