{"total":453,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346,"area":null},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2403.12968","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","created":"2024-03-19","cited_by_count":348,"area":"inference"},{"id":"2503.05592","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","created":"2025-03-07","cited_by_count":336,"area":"lr"},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206,"area":"agents"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203,"area":"inference"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2510.18866","title":"LightMem: Lightweight and Efficient Memory-Augmented Generation","created":"2025-10-21","cited_by_count":180,"area":null},{"id":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166,"area":"mllm"},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136,"area":null},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2409.05591","title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","created":"2024-09-09","cited_by_count":119,"area":"rag"},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119,"area":"lr"},{"id":"2401.18058","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models","created":"2024-01-31","cited_by_count":106,"area":"alignment"},{"id":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105,"area":"rag"},{"id":"2401.03462","title":"Long Context Compression with Activation Beacon","created":"2024-01-07","cited_by_count":104,"area":"inference"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2406.16008","title":"Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization","created":"2024-06-23","cited_by_count":101,"area":null},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83,"area":"rag"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2402.02244","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","created":"2024-02-03","cited_by_count":76,"area":"lr"},{"id":"2311.08734","title":"Thread of Thought Unraveling Chaotic Contexts","created":"2023-11-15","cited_by_count":72,"area":"lr"},{"id":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"area":null},{"id":"2505.14069","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","created":"2025-05-20","cited_by_count":70,"area":"rag"},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"id":"2407.09014","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","created":"2024-07-12","cited_by_count":64,"area":"rag"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2405.10637","title":"Layer-Condensed KV Cache for Efficient Inference of Large Language Models","created":"2024-05-17","cited_by_count":59,"area":"inference"},{"id":"2409.01227","title":"Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference","created":"2024-09-02","cited_by_count":53,"area":"inference"},{"id":"2410.12189","title":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing","created":"2024-10-16","cited_by_count":52,"area":"agents"},{"id":"2406.14528","title":"DeciMamba: Exploring the Length Extrapolation Potential of Mamba","created":"2024-06-20","cited_by_count":49,"area":"ssm"},{"id":"2410.18050","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","created":"2024-10-23","cited_by_count":49,"area":"rag"},{"id":"2503.19213","title":"A Survey of Large Language Model Agents for Question Answering","created":"2025-03-24","cited_by_count":48,"area":"agents"},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47,"area":null},{"id":"2408.03094","title":"500xCompressor: Generalized Prompt Compression for Large Language Models","created":"2024-08-06","cited_by_count":47,"area":"inference"},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2407.21059","title":"Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks","created":"2024-07-26","cited_by_count":42,"area":"rag"},{"id":"2406.15187","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","created":"2024-06-21","cited_by_count":40,"area":"rag"},{"id":"2409.17422","title":"Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction","created":"2024-09-25","cited_by_count":39,"area":"inference"},{"id":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39,"area":null},{"id":"2411.02959","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","created":"2024-11-05","cited_by_count":37,"area":"rag"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36,"area":"rag"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2412.18116","title":"AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation","created":"2024-12-24","cited_by_count":34,"area":"agents"},{"id":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"id":"2603.29919","title":"SkillReducer: Optimizing LLM Agent Skills for Token Efficiency","created":"2026-03-31","cited_by_count":33,"area":"agents"},{"id":"2403.12766","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens","created":"2024-03-18","cited_by_count":32,"area":null},{"id":"2501.07861","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","created":"2025-01-14","cited_by_count":32,"area":"lr"},{"id":"2410.02338","title":"How Much Can RAG Help the Reasoning of LLM?","created":"2024-10-03","cited_by_count":31,"area":"lr"},{"id":"2506.07642","title":"TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review","created":"2025-06-09","cited_by_count":31,"area":null},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2402.12174","title":"BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence","created":"2024-02-19","cited_by_count":28,"area":"rag"},{"id":"2407.15353","title":"Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA","created":"2024-07-22","cited_by_count":28,"area":"rag"},{"id":"2410.04199","title":"LongGenBench: Long-context Generation Benchmark","created":"2024-10-05","cited_by_count":28,"area":null},{"id":"2502.13063","title":"Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity","created":"2025-02-18","cited_by_count":28,"area":"inference"},{"id":"2605.27366","title":"MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation","created":"2026-05-26","cited_by_count":27,"area":"agents"},{"id":"2409.12181","title":"A Controlled Study on Long Context Extension and Generalization in LLMs","created":"2024-09-18","cited_by_count":26,"area":null},{"id":"2410.03227","title":"ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering","created":"2024-10-04","cited_by_count":26,"area":"lr"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2503.01478","title":"SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction","created":"2025-03-03","cited_by_count":24,"area":"rag"},{"id":"2409.19272","title":"Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios","created":"2024-09-28","cited_by_count":23,"area":"inference"},{"id":"2502.11493","title":"DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens","created":"2025-02-17","cited_by_count":22,"area":null},{"id":"2510.07777","title":"Drift No More? Context Equilibria in Multi-Turn LLM Interactions","created":"2025-10-09","cited_by_count":22,"area":null},{"id":"2409.14866","title":"PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs","created":"2024-09-23","cited_by_count":21,"area":"safety"},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2505.12215","title":"GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment","created":"2025-05-18","cited_by_count":21,"area":"inference"},{"id":"2504.18243","title":"DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering","created":"2025-04-25","cited_by_count":20,"area":null},{"id":"2505.17827","title":"Not All Tokens Are What You Need In Thinking","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2406.05317","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","created":"2024-06-08","cited_by_count":19,"area":"inference"},{"id":"2407.15504","title":"Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models","created":"2024-07-22","cited_by_count":19,"area":"inference"},{"id":"2602.02007","title":"Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation","created":"2026-02-02","cited_by_count":19,"area":"rag"},{"id":"2404.00489","title":"Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression","created":"2024-03-30","cited_by_count":18,"area":"inference"},{"id":"2407.08892","title":"Characterizing Prompt Compression Methods for Long Context Inference","created":"2024-07-11","cited_by_count":18,"area":"inference"},{"id":"2501.11551","title":"PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation","created":"2025-01-20","cited_by_count":18,"area":"rag"},{"id":"2508.04664","title":"Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management","created":"2025-08-06","cited_by_count":18,"area":null},{"id":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"area":"rag"},{"id":"2412.17483","title":"A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression","created":"2024-12-23","cited_by_count":17,"area":"inference"},{"id":"2504.01707","title":"InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation","created":"2025-04-02","cited_by_count":17,"area":null},{"id":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"id":"2406.01549","title":"An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation","created":"2024-06-03","cited_by_count":16,"area":"rag"},{"id":"2406.11357","title":"Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities","created":"2024-06-17","cited_by_count":16,"area":"rag"},{"id":"2502.01941","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","created":"2025-02-04","cited_by_count":16,"area":"lr"},{"id":"2503.18174","title":"GINGER: Grounded Information Nugget-Based Generation of Responses","created":"2025-03-23","cited_by_count":16,"area":"rag"},{"id":"2505.10413","title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","created":"2025-05-15","cited_by_count":16,"area":"rag"},{"id":"2510.18586","title":"TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications","created":"2025-10-21","cited_by_count":16,"area":"inference"},{"id":"2503.19114","title":"Understanding and Improving Information Preservation in Prompt Compression for LLMs","created":"2025-03-24","cited_by_count":15,"area":"inference"},{"id":"2407.21443","title":"Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency","created":"2024-07-31","cited_by_count":14,"area":"lr"},{"id":"2502.14317","title":"ParallelComp: Parallel Long-Context Compressor for Length Extrapolation","created":"2025-02-20","cited_by_count":14,"area":"inference"},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"id":"2510.08907","title":"Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors","created":"2025-10-10","cited_by_count":14,"area":"inference"},{"id":"2604.01664","title":"ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents","created":"2026-04-02","cited_by_count":14,"area":"agents"},{"id":"2607.05378","title":"CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents","created":"2026-07-06","cited_by_count":14,"area":"lr"}],"next_cursor":"100"}