{"total":97,"rows":[{"id":"2410.02644","title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","created":"2024-10-03","cited_by_count":369,"area":"agents"},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2406.13629","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","created":"2024-06-19","cited_by_count":101,"area":"rag"},{"id":"2409.12959","title":"MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines","created":"2024-09-19","cited_by_count":101,"area":null},{"id":"2410.20724","title":"Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation","created":"2024-10-28","cited_by_count":80,"area":"lr"},{"id":"2504.13079","title":"Retrieval-Augmented Generation with Conflicting Evidence","created":"2025-04-17","cited_by_count":63,"area":"rag"},{"id":"2410.07176","title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","created":"2024-10-09","cited_by_count":58,"area":"rag"},{"id":"2509.07968","title":"SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge","created":"2025-09-09","cited_by_count":54,"area":null},{"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":"2601.20975","title":"DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents","created":"2026-01-28","cited_by_count":50,"area":"agents"},{"id":"2506.12103","title":"The Amazon Nova Family of Models: Technical Report and Model Card","created":"2025-03-17","cited_by_count":41,"area":null},{"id":"2510.23587","title":"A Survey of Data Agents: Emerging Paradigm or Overstated Hype?","created":"2025-10-27","cited_by_count":30,"area":"agents"},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2409.20163","title":"MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants","created":"2024-09-30","cited_by_count":24,"area":"agents"},{"id":"2407.12873","title":"Evaluation of RAG Metrics for Question Answering in the Telecom Domain","created":"2024-07-15","cited_by_count":20,"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":"2503.14649","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","created":"2025-03-18","cited_by_count":19,"area":"rag"},{"id":"2506.10408","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","created":"2025-06-12","cited_by_count":19,"area":"lr"},{"id":"2505.18543","title":"Benchmarking Poisoning Attacks against Retrieval-Augmented Generation","created":"2025-05-24","cited_by_count":18,"area":"rag"},{"id":"2512.10791","title":"The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality","created":"2025-12-11","cited_by_count":17,"area":null},{"id":"2505.15872","title":"InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation","created":"2025-05-21","cited_by_count":15,"area":"rag"},{"id":"2510.02044","title":"Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage","created":"2025-10-02","cited_by_count":15,"area":"rag"},{"id":"2410.13716","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","created":"2024-10-17","cited_by_count":14,"area":"rag"},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2510.10397","title":"AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval","created":"2025-10-12","cited_by_count":11,"area":null},{"id":"2510.26160","title":"CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark","created":"2025-10-30","cited_by_count":10,"area":"rag"},{"id":"2408.05141","title":"A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning","created":"2024-08-09","cited_by_count":8,"area":"lr"},{"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":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2412.07420","title":"RAG-based Question Answering over Heterogeneous Data and Text","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2501.09928","title":"Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs","created":"2025-01-17","cited_by_count":7,"area":"rag"},{"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":"2601.02391","title":"WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables","created":"2025-12-25","cited_by_count":7,"area":null},{"id":"2601.14952","title":"CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2411.00744","title":"CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG","created":"2024-11-01","cited_by_count":6,"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":"2511.17908","title":"Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction","created":"2025-11-22","cited_by_count":6,"area":"rag"},{"id":"2512.16883","title":"AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":null},{"id":"2504.14858","title":"Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization","created":"2025-04-21","cited_by_count":5,"area":"lr"},{"id":"2505.20266","title":"syftr: Pareto-Optimal Generative AI","created":"2025-05-26","cited_by_count":5,"area":"rag"},{"id":"2511.20227","title":"HKRAG: Holistic Knowledge Retrieval-Augmented Generation Over Visually-Rich Documents","created":"2025-11-25","cited_by_count":5,"area":"rag"},{"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":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"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":"2508.02016","title":"Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations","created":"2025-08-04","cited_by_count":4,"area":"rag"},{"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":"2603.04403","title":"FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents","created":"2026-01-02","cited_by_count":4,"area":null},{"id":"2502.15690","title":"Level-Navi Agent: A Framework and benchmark for Chinese Web Search Agents","created":"2024-12-20","cited_by_count":3,"area":"agents"},{"id":"2602.00593","title":"Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes","created":"2026-01-31","cited_by_count":3,"area":"mllm"},{"id":"2603.18012","title":"DynaRAG: Bridging Static and Dynamic Knowledge in Retrieval-Augmented Generation","created":"2026-02-24","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":"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":"2510.19181","title":"Interpretable Question Answering with Knowledge Graphs","created":"2025-10-22","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":"2512.22195","title":"MatKV: Trading Compute for Flash Storage in LLM Inference","created":"2025-12-20","cited_by_count":2,"area":"rag"},{"id":"2601.11443","title":"Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation","created":"2026-01-16","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":"2605.01688","title":"GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory","created":"2026-05-03","cited_by_count":2,"area":null},{"id":"2605.08518","title":"Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge","created":"2026-05-08","cited_by_count":2,"area":"safety"},{"id":"2506.14412","title":"RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition","created":"2025-06-17","cited_by_count":1,"area":"rag"},{"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":"2603.25164","title":"PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems","created":"2026-03-26","cited_by_count":1,"area":"rag"},{"id":"2604.06211","title":"Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models","created":"2026-03-16","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":"2604.14683","title":"DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation","created":"2026-04-16","cited_by_count":1,"area":"agents"},{"id":"2606.17660","title":"TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2412.14581","title":"CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation","created":"2024-12-19","cited_by_count":0,"area":"rag"},{"id":"2502.20854","title":"A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generation","created":"2025-02-28","cited_by_count":0,"area":"rag"},{"id":"2504.12323","title":"The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation","created":"2025-04-11","cited_by_count":0,"area":"rag"},{"id":"2507.04942","title":"SIGIR 2025 -- LiveRAG Challenge Report","created":"2025-07-07","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":"2508.12282","title":"A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation","created":"2025-08-17","cited_by_count":0,"area":"lr"},{"id":"2509.05703","title":"Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis","created":"2025-09-06","cited_by_count":0,"area":"mllm"},{"id":"2510.18455","title":"ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks","created":"2025-10-21","cited_by_count":0,"area":"rag"},{"id":"2604.20850","title":"Association Is Not Similarity: Learning Corpus-Specific Associations for Multi-Hop Retrieval","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2604.26176","title":"CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering","created":"2026-04-28","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},{"id":"2605.10168","title":"ASTRA-QA: A Benchmark for Abstract Question Answering over Documents","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.22829","title":"LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding","created":"2026-04-18","cited_by_count":0,"area":"rag"},{"id":"2605.26476","title":"FAB-Bench: A Framework for Adaptive RAG Benchmarking in Semiconductor Manufacturing","created":"2026-05-26","cited_by_count":0,"area":"rag"},{"id":"2605.28508","title":"Benchmarking AI for low-resource contexts: Thinking beyond leaderboards","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.28522","title":"Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability","created":"2026-05-27","cited_by_count":0,"area":"rag"},{"id":"2605.31010","title":"MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation","created":"2026-05-29","cited_by_count":0,"area":"rag"},{"id":"2606.11562","title":"GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.17649","title":"A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.25533","title":"Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems","created":"2026-06-24","cited_by_count":0,"area":"rag"},{"id":"2607.05484","title":"SHARC: SHAP-Based Interpretability in Machine Learning Risk Models for Regulatory Capital under ICAAP and CCAR","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.27353","title":"LayerRAG-Bench: A Cross-Layer Reliability Benchmark for Agentic Retrieval-Augmented Generation","created":"2026-07-29","cited_by_count":0,"area":"rag"},{"id":"2608.00054","title":"RAG-TESTER: Automated End-to-End Testing of Retrieval-Augmented Large Language Models","created":"2026-07-26","cited_by_count":0,"area":"rag"},{"id":"2608.12282","title":"VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2609.00763","title":"Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History Textbooks","created":"2026-09-01","cited_by_count":0,"area":"rag"},{"id":"2609.05139","title":"NS-ST-GraphRAG: Neuro-Symbolic Spatio-Temporal GraphRAG for Literary Knowledge Processing","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2609.11082","title":"ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.34179","title":"RAGWarrant: Evidence-Preserving Governance for RAG Policy Promotion Under Quality, Cost, Latency, and Risk Constraints","created":"2026-09-28","cited_by_count":0,"area":"rag"},{"id":"2609.37469","title":"Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG","created":"2026-09-27","cited_by_count":0,"area":"rag"},{"id":"2610.04691","title":"RAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation","created":"2026-10-03","cited_by_count":0,"area":"rag"},{"id":"2610.20419","title":"Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks","created":"2026-10-14","cited_by_count":0,"area":"rag"}],"next_cursor":null}