{"total":125,"rows":[{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2406.13629","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","created":"2024-06-19","cited_by_count":101,"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":"2407.09014","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","created":"2024-07-12","cited_by_count":64,"area":"rag"},{"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":"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":"2505.00675","title":"Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics","created":"2025-05-01","cited_by_count":36,"area":"lr"},{"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":"2407.09252","title":"Context Embeddings for Efficient Answer Generation in RAG","created":"2024-07-12","cited_by_count":26,"area":"rag"},{"id":"2503.23895","title":"Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement","created":"2025-03-31","cited_by_count":25,"area":"rag"},{"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":"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":"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":"2406.14848","title":"Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models","created":"2024-06-21","cited_by_count":20,"area":null},{"id":"2501.16075","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","created":"2025-01-27","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":"2508.01832","title":"MLP Memory: A Retriever-Pretrained Memory for Large Language Models","created":"2025-08-03","cited_by_count":20,"area":"rag"},{"id":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2503.10720","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","created":"2025-03-13","cited_by_count":19,"area":"rag"},{"id":"2410.10293","title":"FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG","created":"2024-10-14","cited_by_count":18,"area":"rag"},{"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":"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":"2505.10413","title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","created":"2025-05-15","cited_by_count":16,"area":"rag"},{"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":"2505.17670","title":"Towards General Continuous Memory for Vision-Language Models","created":"2025-05-23","cited_by_count":15,"area":"mllm"},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"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":"2511.18659","title":"CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning","created":"2025-11-24","cited_by_count":11,"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":"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":"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":"2507.22931","title":"Enhancing RAG Efficiency with Adaptive Context Compression","created":"2025-07-24","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":"2512.04550","title":"AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees","created":"2025-12-04","cited_by_count":8,"area":"inference"},{"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":"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":"2510.20797","title":"No Mean Feat: Simple, Strong Baselines for Context Compression","created":"2025-10-23","cited_by_count":7,"area":"inference"},{"id":"2412.07393","title":"CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models","created":"2024-12-10","cited_by_count":6,"area":null},{"id":"2601.12906","title":"Gated Differentiable Working Memory for Long-Context Language Modeling","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2606.04557","title":"Cartridges at Scale: Training Modular KV Caches over Large Document Collections","created":"2026-06-03","cited_by_count":6,"area":"inference"},{"id":"2508.15253","title":"Conflict-Aware Soft Prompting for Retrieval-Augmented Generation","created":"2025-08-21","cited_by_count":5,"area":"rag"},{"id":"2509.19228","title":"CompLLM: Compression for Long Context Q&A","created":"2025-09-23","cited_by_count":5,"area":"inference"},{"id":"2602.00746","title":"Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression","created":"2026-01-31","cited_by_count":5,"area":"mllm"},{"id":"2602.03226","title":"ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2503.06484","title":"Sign Language Translation using Frame and Event Stream: Benchmark Dataset and Algorithms","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","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":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2607.08032","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","created":"2026-07-09","cited_by_count":4,"area":"agents"},{"id":"2505.13434","title":"SMOTExT: SMOTE meets Large Language Models","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2507.13874","title":"Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models","created":"2025-07-18","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2510.20535","title":"ARC-Encoder: learning compressed text representations for large language models","created":"2025-10-23","cited_by_count":3,"area":"lr"},{"id":"2510.26615","title":"SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2511.17129","title":"Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2410.09623","title":"Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation","created":"2024-10-12","cited_by_count":2,"area":"rag"},{"id":"2410.21012","title":"FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2502.10976","title":"QuOTE: Question-Oriented Text Embeddings","created":"2025-02-16","cited_by_count":2,"area":"rag"},{"id":"2503.19574","title":"Context-Efficient Retrieval with Factual Decomposition","created":"2025-03-25","cited_by_count":2,"area":null},{"id":"2511.18832","title":"Concept than Document: Context Compression via AMR-based Conceptual Entropy","created":"2025-11-24","cited_by_count":2,"area":"rag"},{"id":"2601.13222","title":"Incorporating Q&A Nuggets into Retrieval-Augmented Generation","created":"2026-01-19","cited_by_count":2,"area":"rag"},{"id":"2601.18886","title":"XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation","created":"2026-01-26","cited_by_count":2,"area":"rag"},{"id":"2602.03784","title":"Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"id":"2603.10913","title":"LLM2Vec-Gen: Generative Embeddings from Large Language Models","created":"2026-03-11","cited_by_count":2,"area":"safety"},{"id":"2607.18213","title":"SWE-Pruner Pro: The Coder LLM Already Knows What to Prune","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2609.35621","title":"Cartridges++: KV Cache Compression without Off-Context Derailment","created":"2026-09-28","cited_by_count":2,"area":"inference"},{"id":"2407.01403","title":"Optimization of Retrieval-Augmented Generation Context with Outlier Detection","created":"2024-07-01","cited_by_count":1,"area":"rag"},{"id":"2503.01606","title":"Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2508.05909","title":"Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score","created":"2025-08-08","cited_by_count":1,"area":"rag"},{"id":"2601.05038","title":"ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG","created":"2026-01-08","cited_by_count":1,"area":"rag"},{"id":"2601.10644","title":"RoutIR: Fast Serving of Retrieval Pipelines for Retrieval-Augmented Generation","created":"2026-01-15","cited_by_count":1,"area":"rag"},{"id":"2602.01778","title":"Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model","created":"2026-02-02","cited_by_count":1,"area":"inference"},{"id":"2602.10021","title":"Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2602.12235","title":"Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation","created":"2026-02-12","cited_by_count":1,"area":"rag"},{"id":"2602.13980","title":"Cognitive Chunking for Soft Prompts: Accelerating Compressor Learning via Block-wise Causal Masking","created":"2026-02-15","cited_by_count":1,"area":null},{"id":"2603.08819","title":"Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage","created":"2026-03-09","cited_by_count":1,"area":"rag"},{"id":"2604.17866","title":"Latent Abstraction for Retrieval-Augmented Generation","created":"2026-04-20","cited_by_count":1,"area":"rag"},{"id":"2604.23734","title":"Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval","created":"2026-04-26","cited_by_count":1,"area":"rag"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2605.30790","title":"On the impact of retrieved content representations in RAG Pipelines","created":"2026-05-29","cited_by_count":1,"area":"rag"},{"id":"2606.21807","title":"Fixed RAG Compression Collapses Measured Reader Scaling","created":"2026-06-20","cited_by_count":1,"area":"rag"},{"id":"2608.13588","title":"IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering","created":"2026-07-12","cited_by_count":1,"area":"rag"},{"id":"2608.22752","title":"The Compaction Cliff in Long-Running AI Agent Memory","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2609.01507","title":"LatentPress: Context Compression Beyond Text and Vision","created":"2026-09-01","cited_by_count":1,"area":"inference"},{"id":"2609.25537","title":"Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"id":"2609.27298","title":"StateComp: Learning When to Compress History in Long Horizon Agents","created":"2026-09-23","cited_by_count":1,"area":"agents"},{"id":"2508.01084","title":"Provably Secure Retrieval-Augmented Generation","created":"2025-08-01","cited_by_count":0,"area":"rag"},{"id":"2510.05363","title":"MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2510.22963","title":"When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents","created":"2025-10-27","cited_by_count":0,"area":"agents"},{"id":"2601.08209","title":"Generation-Augmented Generation: A Plug-and-Play Framework for Private Knowledge Injection in Large Language Models","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2602.01567","title":"DREAMS: A Social Exchange Theory-Informed Modeling of Misinformation Engagement on Social Media","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.09347","title":"The Virtuous Cycle: AI-Powered Vector Search and Vector Search-Augmented AI","created":"2026-03-10","cited_by_count":0,"area":"rag"},{"id":"2603.25926","title":"Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio","created":"2026-03-26","cited_by_count":0,"area":"inference"},{"id":"2604.14403","title":"A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation","created":"2026-04-15","cited_by_count":0,"area":"rag"},{"id":"2604.15153","title":"Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models","created":"2026-04-16","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}