{"total":77,"rows":[{"id":"2411.06037","title":"Sufficient Context: A New Lens on Retrieval Augmented Generation Systems","created":"2024-11-09","cited_by_count":72,"area":"rag"},{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","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":"2411.00300","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","created":"2024-11-01","cited_by_count":41,"area":"rag"},{"id":"2411.04975","title":"SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications","created":"2024-11-07","cited_by_count":36,"area":"agents"},{"id":"2410.06458","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","created":"2024-10-09","cited_by_count":35,"area":"lr"},{"id":"2507.22424","title":"Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance","created":"2025-07-30","cited_by_count":32,"area":"mllm"},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2502.19732","title":"Speculative Decoding and Beyond: An In-Depth Survey of Techniques","created":"2025-02-27","cited_by_count":23,"area":"inference"},{"id":"2410.05589","title":"ParallelSpec: Parallel Drafter for Efficient Speculative Decoding","created":"2024-10-08","cited_by_count":22,"area":"inference"},{"id":"2508.10391","title":"LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval","created":"2025-08-14","cited_by_count":16,"area":"rag"},{"id":"2502.20330","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","created":"2025-02-27","cited_by_count":14,"area":"rag"},{"id":"2505.19201","title":"DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding","created":"2025-05-25","cited_by_count":14,"area":"mllm"},{"id":"2503.19878","title":"CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation","created":"2025-03-25","cited_by_count":12,"area":"rag"},{"id":"2412.05838","title":"A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data","created":"2024-12-08","cited_by_count":10,"area":"rag"},{"id":"2505.13204","title":"Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification","created":"2025-05-19","cited_by_count":10,"area":"inference"},{"id":"2510.13975","title":"Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems","created":"2025-10-15","cited_by_count":10,"area":"rag"},{"id":"2502.20969","title":"TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval","created":"2025-02-28","cited_by_count":9,"area":"rag"},{"id":"2505.23052","title":"RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models","created":"2025-05-29","cited_by_count":8,"area":"rag"},{"id":"2505.12731","title":"Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps","created":"2025-05-19","cited_by_count":6,"area":"rag"},{"id":"2506.02097","title":"Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation","created":"2025-06-02","cited_by_count":6,"area":"rag"},{"id":"2504.01281","title":"Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding","created":"2025-04-02","cited_by_count":5,"area":"rag"},{"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":"2505.17391","title":"Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2503.08398","title":"OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning","created":"2025-03-11","cited_by_count":4,"area":"rag"},{"id":"2505.17118","title":"After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation","created":"2025-05-21","cited_by_count":4,"area":"rag"},{"id":"2507.21110","title":"SemRAG: Semantic Knowledge-Augmented RAG for Improved Question-Answering","created":"2025-07-10","cited_by_count":4,"area":"rag"},{"id":"2602.15318","title":"Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs","created":"2026-02-17","cited_by_count":4,"area":"mllm"},{"id":"2603.23049","title":"PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving","created":"2026-03-24","cited_by_count":4,"area":"rag"},{"id":"2506.03546","title":"From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Context","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2604.05821","title":"CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2604.10740","title":"RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game","created":"2026-04-12","cited_by_count":3,"area":"agents"},{"id":"2501.16276","title":"URAG: Implementing a Unified Hybrid RAG for Precise Answers in University Admission Chatbots -- A Case Study at HCMUT","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2504.15302","title":"RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU","created":"2025-04-17","cited_by_count":2,"area":"rag"},{"id":"2511.14182","title":"WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web","created":"2025-11-18","cited_by_count":2,"area":"rag"},{"id":"2511.14772","title":"Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2604.07937","title":"HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2605.21965","title":"SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2412.17558","title":"A Survey of Query Optimization in Large Language Models","created":"2024-12-23","cited_by_count":1,"area":"rag"},{"id":"2412.17942","title":"Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents","created":"2024-12-23","cited_by_count":1,"area":"agents"},{"id":"2503.00491","title":"Tutorial Proposal: Speculative Decoding for Efficient LLM Inference","created":"2025-03-01","cited_by_count":1,"area":"inference"},{"id":"2503.05530","title":"Leveraging Approximate Caching for Faster Retrieval-Augmented Generation","created":"2025-03-07","cited_by_count":1,"area":"rag"},{"id":"2503.20309","title":"Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs","created":"2025-03-26","cited_by_count":1,"area":"mllm"},{"id":"2503.23523","title":"Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models","created":"2025-03-30","cited_by_count":1,"area":null},{"id":"2504.03302","title":"Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2510.24652","title":"Optimizing Retrieval for RAG via Reinforcement Learning","created":"2025-10-28","cited_by_count":1,"area":"lr"},{"id":"2511.05919","title":"Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2601.01513","title":"FastV-RAG: Towards Fast and Fine-Grained Video QA with Retrieval-Augmented Generation","created":"2026-01-04","cited_by_count":1,"area":"lr"},{"id":"2601.05465","title":"PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering","created":"2026-01-09","cited_by_count":1,"area":"rag"},{"id":"2602.00083","title":"SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation","created":"2026-01-22","cited_by_count":1,"area":"rag"},{"id":"2602.01068","title":"From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization","created":"2026-02-01","cited_by_count":1,"area":"alignment"},{"id":"2604.25931","title":"Anchored Confabulation: Partial Evidence Non-Monotonically Amplifies Confident Hallucination in LLMs","created":"2026-04-02","cited_by_count":1,"area":"lr"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2605.28046","title":"MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.07235","title":"FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A","created":"2026-06-05","cited_by_count":1,"area":"rag"},{"id":"2606.13438","title":"CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"id":"2609.26086","title":"CoVeR: Coverage-Based Routing of Verifier Calls in Agentic Retrieval","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2501.00562","title":"An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems","created":"2024-12-31","cited_by_count":0,"area":null},{"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":"2505.07833","title":"Harmonia: End-to-End RAG Serving Optimization","created":"2025-05-01","cited_by_count":0,"area":"rag"},{"id":"2505.17206","title":"FB-RAG: Improving RAG with Forward and Backward Lookup","created":"2025-05-22","cited_by_count":0,"area":"rag"},{"id":"2507.12443","title":"LLM-Based Config Synthesis requires Disambiguation","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2510.00088","title":"Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail Prediction","created":"2025-09-30","cited_by_count":0,"area":"mllm"},{"id":"2510.01427","title":"A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2511.04700","title":"Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation","created":"2025-11-01","cited_by_count":0,"area":"rag"},{"id":"2604.08046","title":"Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation","created":"2026-04-09","cited_by_count":0,"area":"rag"},{"id":"2604.20452","title":"HaS: Accelerating RAG through Homology-Aware Speculative Retrieval","created":"2026-04-22","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":"2605.11186","title":"CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration","created":"2026-05-11","cited_by_count":0,"area":"inference"},{"id":"2605.17989","title":"Predictive Prefetching for Retrieval-Augmented Generation","created":"2026-05-18","cited_by_count":0,"area":"rag"},{"id":"2606.17449","title":"MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation","created":"2026-06-16","cited_by_count":0,"area":"mllm"},{"id":"2608.14797","title":"Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models","created":"2026-08-14","cited_by_count":0,"area":"mllm"},{"id":"2608.23252","title":"The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2608.26732","title":"Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.31047","title":"DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2610.01936","title":"Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}