{"total":119,"rows":[{"id":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123,"area":"rag"},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66,"area":"inference"},{"id":"2409.01666","title":"In Defense of RAG in the Era of Long-Context Language Models","created":"2024-09-03","cited_by_count":53,"area":"rag"},{"id":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39,"area":"rag"},{"id":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39,"area":null},{"id":"2412.15605","title":"Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks","created":"2024-12-20","cited_by_count":38,"area":"rag"},{"id":"2507.18910","title":"A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions","created":"2025-07-25","cited_by_count":31,"area":"rag"},{"id":"2412.16311","title":"HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases","created":"2024-12-20","cited_by_count":29,"area":"rag"},{"id":"2502.09977","title":"LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing","created":"2025-02-14","cited_by_count":29,"area":"rag"},{"id":"2506.00054","title":"Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers","created":"2025-05-28","cited_by_count":27,"area":"rag"},{"id":"2412.14468","title":"HashAttention: Semantic Sparsity for Faster Inference","created":"2024-12-19","cited_by_count":24,"area":null},{"id":"2411.03538","title":"Long Context RAG Performance of Large Language Models","created":"2024-11-05","cited_by_count":23,"area":null},{"id":"2502.00330","title":"From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation","created":"2025-02-01","cited_by_count":21,"area":"lr"},{"id":"2506.08479","title":"Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-$k$","created":"2025-06-10","cited_by_count":21,"area":"rag"},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2503.00353","title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","created":"2025-03-01","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":"2504.15800","title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","created":"2025-04-22","cited_by_count":17,"area":"rag"},{"id":"2505.11545","title":"TARGET: Benchmarking Table Retrieval for Generative Tasks","created":"2025-05-14","cited_by_count":17,"area":null},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16,"area":"rag"},{"id":"2410.10450","title":"KBLaM: Knowledge Base augmented Language Model","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2502.02789","title":"Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation","created":"2025-02-05","cited_by_count":14,"area":null},{"id":"2502.20330","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","created":"2025-02-27","cited_by_count":14,"area":"rag"},{"id":"2601.06037","title":"TeleMem: Building Long-Term and Multimodal Memory for Agentic AI","created":"2025-12-12","cited_by_count":14,"area":"agents"},{"id":"2603.20432","title":"Coding Agents are Effective Long-Context Processors","created":"2026-03-20","cited_by_count":12,"area":"agents"},{"id":"2410.11996","title":"Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data","created":"2024-10-15","cited_by_count":11,"area":"lr"},{"id":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11,"area":"synth"},{"id":"2511.18659","title":"CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning","created":"2025-11-24","cited_by_count":11,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2412.17031","title":"A Reality Check on Context Utilisation for Retrieval-Augmented Generation","created":"2024-12-22","cited_by_count":9,"area":"rag"},{"id":"2505.08120","title":"Putting It All into Context: Simplifying Agents with LCLMs","created":"2025-05-12","cited_by_count":9,"area":"agents"},{"id":"2506.03989","title":"Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models","created":"2025-06-04","cited_by_count":9,"area":"rag"},{"id":"2506.06091","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2508.16994","title":"GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation","created":"2025-08-23","cited_by_count":8,"area":"rag"},{"id":"2510.18279","title":"Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs","created":"2025-10-21","cited_by_count":8,"area":"mllm"},{"id":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"id":"2511.17560","title":"$A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving","created":"2025-11-13","cited_by_count":8,"area":"rag"},{"id":"2602.15313","title":"Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory","created":"2026-02-17","cited_by_count":8,"area":null},{"id":"2508.01503","title":"A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents","created":"2025-08-02","cited_by_count":7,"area":"agents"},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2505.07793","title":"Overflow Prevention Enhances Long-Context Recurrent LLMs","created":"2025-05-12","cited_by_count":6,"area":"ssm"},{"id":"2510.05688","title":"vAttention: Verified Sparse Attention","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2510.08109","title":"VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents","created":"2025-10-09","cited_by_count":6,"area":"rag"},{"id":"2510.20941","title":"Do LLMs Truly Understand When a Precedent Is Overruled?","created":"2025-10-23","cited_by_count":6,"area":null},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"id":"2606.22844","title":"RaMem: Contextual Reinstatement for Long-term Agentic Memory","created":"2026-06-22","cited_by_count":6,"area":"agents"},{"id":"2410.02115","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2507.04723","title":"LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2507.18202","title":"Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection","created":"2025-07-24","cited_by_count":5,"area":"rag"},{"id":"2511.01386","title":"RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets","created":"2025-11-03","cited_by_count":5,"area":"rag"},{"id":"2601.17212","title":"DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation","created":"2026-01-23","cited_by_count":5,"area":"rag"},{"id":"2608.12875","title":"The Embedder's Dilemma: LLMs Are Better, but at What Cost?","created":"2026-08-13","cited_by_count":5,"area":"lr"},{"id":"2411.18831","title":"Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark","created":"2024-11-28","cited_by_count":4,"area":null},{"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":"2508.14817","title":"Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs","created":"2025-08-20","cited_by_count":4,"area":"lr"},{"id":"2510.24402","title":"Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering","created":"2025-10-28","cited_by_count":4,"area":"rag"},{"id":"2512.24684","title":"R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory","created":"2025-12-31","cited_by_count":4,"area":"rag"},{"id":"2605.20084","title":"BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation","created":"2026-05-19","cited_by_count":4,"area":"rag"},{"id":"2503.16575","title":"Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2505.02763","title":"Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2505.11754","title":"Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2506.01215","title":"Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers","created":"2025-06-01","cited_by_count":3,"area":"inference"},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2601.17532","title":"Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection","created":"2026-01-24","cited_by_count":3,"area":"rag"},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2603.20105","title":"The $\\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $\\lambda$-Calculus","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2409.12524","title":"Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting","created":"2024-09-19","cited_by_count":2,"area":"rag"},{"id":"2501.16220","title":"DBRouting: Routing End User Queries to Databases for Answerability","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2503.02603","title":"OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing","created":"2025-03-04","cited_by_count":2,"area":"rag"},{"id":"2504.16204","title":"Reflexive Prompt Engineering: A Framework for Responsible Prompt Engineering and Interaction Design","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2505.12662","title":"Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering","created":"2025-05-19","cited_by_count":2,"area":"rag"},{"id":"2505.18092","title":"QwenLong-CPRS: Towards $\\infty$-LLMs with Dynamic Context Optimization","created":"2025-05-23","cited_by_count":2,"area":"inference"},{"id":"2509.25973","title":"Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions","created":"2025-09-30","cited_by_count":2,"area":"safety"},{"id":"2510.19875","title":"Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention","created":"2025-10-22","cited_by_count":2,"area":"mechinterp"},{"id":"2601.13007","title":"ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2602.13418","title":"Text Has Curvature","created":"2026-02-13","cited_by_count":2,"area":null},{"id":"2602.22175","title":"DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2604.26981","title":"Budget-Constrained Online Retrieval-Augmented Generation: The Chunk-as-a-Service Model","created":"2026-04-28","cited_by_count":2,"area":"rag"},{"id":"2607.15657","title":"Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents","created":"2026-07-17","cited_by_count":2,"area":"agents"},{"id":"2410.13037","title":"LFOSum: Summarizing Long-form Opinions with Large Language Models","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2504.12972","title":"Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization","created":"2025-04-17","cited_by_count":1,"area":"lr"},{"id":"2506.00049","title":"Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models","created":"2025-05-28","cited_by_count":1,"area":"lr"},{"id":"2507.08704","title":"Knowledge Fusion via Bidirectional Information Aggregation","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2601.18527","title":"Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models","created":"2026-01-26","cited_by_count":1,"area":"rag"},{"id":"2602.18448","title":"INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2603.14778","title":"P$^2$RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval","created":"2026-03-16","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":"2606.04231","title":"MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.13550","title":"Uncertainty-Aware Hybrid Retrieval for Long-Document RAG","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"id":"2606.20898","title":"The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2411.07870","title":"Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2505.17206","title":"FB-RAG: Improving RAG with Forward and Backward Lookup","created":"2025-05-22","cited_by_count":0,"area":"rag"},{"id":"2506.12149","title":"Maximally-Informative Retrieval for State Space Model Generation","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2508.18093","title":"Agri-Query: A Case Study on RAG vs. Long-Context LLMs for Cross-Lingual Technical Question Answering","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2509.21865","title":"Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding","created":"2025-09-26","cited_by_count":0,"area":"rag"},{"id":"2511.06125","title":"Evaluation of retrieval-based QA on QUEST-LOFT","created":"2025-11-08","cited_by_count":0,"area":"rag"},{"id":"2512.08088","title":"Adaptation of Embedding Models to Financial Filings via LLM Distillation","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.15658","title":"Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.24376","title":"GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization","created":"2026-03-25","cited_by_count":0,"area":null}],"next_cursor":"100"}