{"total":348,"rows":[{"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":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249,"area":"lr"},{"id":"2510.18866","title":"LightMem: Lightweight and Efficient Memory-Augmented Generation","created":"2025-10-21","cited_by_count":180,"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":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119,"area":"lr"},{"id":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105,"area":"rag"},{"id":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95,"area":"inference"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"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":"2407.09014","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","created":"2024-07-12","cited_by_count":64,"area":"rag"},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"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":"2509.23586","title":"Reducing Cost of LLM Agents with Trajectory Reduction","created":"2025-09-28","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":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2512.22087","title":"Context as a Tool: Context Management for Long-Horizon SWE-Agents","created":"2025-12-26","cited_by_count":43,"area":"agents"},{"id":"2602.15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","created":"2026-02-13","cited_by_count":43,"area":"lr"},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"area":"inference"},{"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":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2410.02338","title":"How Much Can RAG Help the Reasoning of LLM?","created":"2024-10-03","cited_by_count":31,"area":"lr"},{"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":"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":"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":"2408.04259","title":"EfficientRAG: Efficient Retriever for Multi-Hop Question Answering","created":"2024-08-08","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":"2409.13035","title":"TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning","created":"2024-09-19","cited_by_count":22,"area":"lr"},{"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":"2510.05069","title":"SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs","created":"2025-10-06","cited_by_count":22,"area":"lr"},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2503.17439","title":"LEMMA: Learning from Errors for MatheMatical Advancement in LLMs","created":"2025-03-21","cited_by_count":21,"area":"lr"},{"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":"2601.04463","title":"Beyond Static Summarization: Proactive Memory Extraction for LLM Agents","created":"2026-01-08","cited_by_count":21,"area":"agents"},{"id":"2601.13879","title":"Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring","created":"2026-01-20","cited_by_count":21,"area":"lr"},{"id":"2501.16075","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","created":"2025-01-27","cited_by_count":20,"area":"rag"},{"id":"2505.17827","title":"Not All Tokens Are What You Need In Thinking","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"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":"2503.10720","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","created":"2025-03-13","cited_by_count":19,"area":"rag"},{"id":"2505.14582","title":"Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning","created":"2025-05-20","cited_by_count":19,"area":"lr"},{"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":"2508.04664","title":"Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management","created":"2025-08-06","cited_by_count":18,"area":null},{"id":"2407.09025","title":"SpreadsheetLLM: Encoding Spreadsheets for Large Language Models","created":"2024-07-12","cited_by_count":17,"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":"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":"2507.08143","title":"Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores","created":"2025-07-10","cited_by_count":17,"area":"inference"},{"id":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"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":"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":"2505.19716","title":"Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting","created":"2025-05-26","cited_by_count":15,"area":"lr"},{"id":"2604.19572","title":"A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression","created":"2026-04-21","cited_by_count":15,"area":"inference"},{"id":"2502.20330","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","created":"2025-02-27","cited_by_count":14,"area":"rag"},{"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":"2406.19251","title":"AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation","created":"2024-06-27","cited_by_count":13,"area":"rag"},{"id":"2407.02211","title":"PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning","created":"2024-07-02","cited_by_count":13,"area":null},{"id":"2504.08934","title":"Long Context In-Context Compression by Getting to the Gist of Gisting","created":"2025-04-11","cited_by_count":13,"area":"inference"},{"id":"2506.12707","title":"SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression","created":"2025-06-15","cited_by_count":13,"area":"inference"},{"id":"2508.00574","title":"SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought","created":"2025-08-01","cited_by_count":13,"area":"lr"},{"id":"2602.01719","title":"COMI: Coarse-to-fine Context Compression via Marginal Information Gain","created":"2026-02-02","cited_by_count":13,"area":"inference"},{"id":"2605.12357","title":"$\\delta$-mem: Efficient Online Memory for Large Language Models","created":"2026-05-12","cited_by_count":13,"area":null},{"id":"2501.12959","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","created":"2025-01-22","cited_by_count":12,"area":"inference"},{"id":"2505.08392","title":"Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning","created":"2025-05-13","cited_by_count":12,"area":"lr"},{"id":"2508.05282","title":"Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning","created":"2025-08-07","cited_by_count":11,"area":"lr"},{"id":"2511.18659","title":"CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning","created":"2025-11-24","cited_by_count":11,"area":"lr"},{"id":"2409.15895","title":"Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation","created":"2024-09-24","cited_by_count":10,"area":"rag"},{"id":"2505.11166","title":"SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization","created":"2025-05-16","cited_by_count":10,"area":"alignment"},{"id":"2506.08125","title":"Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning","created":"2025-06-09","cited_by_count":10,"area":"lr"},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2507.11953","title":"IAM: Efficient Inference through Attention Mapping between Different-scale LLMs","created":"2025-07-16","cited_by_count":10,"area":"inference"},{"id":"2602.01840","title":"Read As Human: Compressing Context via Parallelizable Close Reading and Skimming","created":"2026-02-02","cited_by_count":10,"area":null},{"id":"2608.06503","title":"Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability","created":"2026-08-06","cited_by_count":10,"area":"inference"},{"id":"2410.07589","title":"No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users","created":"2024-10-10","cited_by_count":9,"area":"rag"},{"id":"2410.10074","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2410.11786","title":"Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability","created":"2024-10-15","cited_by_count":9,"area":"inference"},{"id":"2506.07443","title":"LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2510.16932","title":"Prompt-MII: Meta-Learning Instruction Induction for LLMs","created":"2025-10-19","cited_by_count":9,"area":null},{"id":"2510.25817","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2603.18507","title":"Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM","created":"2026-03-19","cited_by_count":9,"area":"alignment"},{"id":"2604.02985","title":"Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference","created":"2026-04-03","cited_by_count":9,"area":"rag"},{"id":"2411.15927","title":"Generative Prompt Internalization","created":"2024-11-24","cited_by_count":8,"area":null},{"id":"2505.00019","title":"An Empirical Study on Prompt Compression for Large Language Models","created":"2025-04-24","cited_by_count":8,"area":"inference"},{"id":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"area":"alignment"},{"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":"2512.04550","title":"AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees","created":"2025-12-04","cited_by_count":8,"area":"inference"},{"id":"2403.15268","title":"Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering","created":"2024-03-22","cited_by_count":7,"area":"rag"},{"id":"2410.04139","title":"From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression","created":"2024-10-05","cited_by_count":7,"area":"inference"},{"id":"2501.02844","title":"GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification","created":"2025-01-06","cited_by_count":7,"area":"rag"},{"id":"2505.15774","title":"Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention","created":"2025-05-21","cited_by_count":7,"area":"inference"},{"id":"2506.05410","title":"Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs","created":"2025-06-04","cited_by_count":7,"area":"inference"},{"id":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2507.11942","title":"DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression","created":"2025-07-16","cited_by_count":7,"area":"inference"},{"id":"2510.20797","title":"No Mean Feat: Simple, Strong Baselines for Context Compression","created":"2025-10-23","cited_by_count":7,"area":"inference"},{"id":"2511.05549","title":"AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs","created":"2025-11-02","cited_by_count":7,"area":"lr"}],"next_cursor":"100"}