{"total":64,"rows":[{"id":"2506.15841","title":"MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents","created":"2025-06-18","cited_by_count":238,"area":"lr"},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"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":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2501.16214","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","created":"2025-01-27","cited_by_count":25,"area":"rag"},{"id":"2601.04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"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":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"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":"2510.01353","title":"MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments","created":"2025-10-01","cited_by_count":13,"area":"agents"},{"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":"2502.15957","title":"R$^3$Mem: Bridging Memory Retention and Retrieval via Reversible Compression","created":"2025-02-21","cited_by_count":12,"area":null},{"id":"2512.15649","title":"VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?","created":"2025-12-17","cited_by_count":11,"area":"mllm"},{"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":"2512.04550","title":"AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees","created":"2025-12-04","cited_by_count":8,"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":"2502.13465","title":"HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks","created":"2025-02-19","cited_by_count":6,"area":"rag"},{"id":"2508.15813","title":"SCOPE: A Generative Approach for LLM Prompt Compression","created":"2025-08-16","cited_by_count":6,"area":"inference"},{"id":"2602.08324","title":"Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression","created":"2026-02-09","cited_by_count":6,"area":"lr"},{"id":"2602.01766","title":"CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2409.12468","title":"Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":4,"area":"rag"},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","cited_by_count":4,"area":"rag"},{"id":"2506.05167","title":"ECoRAG: Evidentiality-guided Compression for Long Context RAG","created":"2025-06-05","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":"2508.06030","title":"Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2509.17486","title":"AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation","created":"2025-09-22","cited_by_count":3,"area":"rag"},{"id":"2604.16313","title":"MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering","created":"2026-02-01","cited_by_count":3,"area":"rag"},{"id":"2605.09463","title":"Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven","created":"2026-05-10","cited_by_count":3,"area":"inference"},{"id":"2606.11680","title":"Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents","created":"2026-06-10","cited_by_count":3,"area":"agents"},{"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":"2503.04789","title":"Aligning Extraction and Generation for Robust Retrieval-Augmented Generation","created":"2025-02-28","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":"2507.13681","title":"LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues","created":"2025-07-18","cited_by_count":2,"area":"inference"},{"id":"2511.16283","title":"MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answering","created":"2025-11-20","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":"2412.12486","title":"Boosting Long-Context Management via Query-Guided Activation Refilling","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2502.13019","title":"Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation","created":"2025-02-18","cited_by_count":1,"area":"rag"},{"id":"2504.12673","title":"ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models","created":"2025-04-17","cited_by_count":1,"area":"rag"},{"id":"2507.19353","title":"Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2509.15577","title":"Relevance to Utility: Process-Supervised Rewrite for RAG","created":"2025-09-19","cited_by_count":1,"area":"rag"},{"id":"2511.12281","title":"Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor","created":"2025-11-15","cited_by_count":1,"area":"inference"},{"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":"2603.09222","title":"EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering","created":"2026-03-10","cited_by_count":1,"area":"rag"},{"id":"2604.06627","title":"DiffuMask: Diffusion Language Model for Token-level Prompt Pruning","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"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":"2606.21807","title":"Fixed RAG Compression Collapses Measured Reader Scaling","created":"2026-06-20","cited_by_count":1,"area":"rag"},{"id":"2607.01916","title":"ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair","created":"2026-07-02","cited_by_count":1,"area":"agents"},{"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":"2512.08943","title":"Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models","created":"2025-11-19","cited_by_count":0,"area":"rag"},{"id":"2604.17325","title":"Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation","created":"2026-04-19","cited_by_count":0,"area":"rag"},{"id":"2606.01336","title":"LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning","created":"2026-05-31","cited_by_count":0,"area":"inference"},{"id":"2606.03197","title":"MemTrain: Self-Supervised Context Memory Training","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.06906","title":"EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.15641","title":"Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2607.08180","title":"Out of Sight: Compression-Aware Content Protection against Agentic Crawlers","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2608.03148","title":"Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation","created":"2026-08-04","cited_by_count":0,"area":"rag"},{"id":"2608.26949","title":"A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.05152","title":"Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2609.11209","title":"REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.28771","title":"Agent Memory with Episodic Retrieval for Financial Decision-Making","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.31505","title":"Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32269","title":"Before Answering: Evidence Sufficiency under Size-Matched Memory Construction","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37930","title":"Learning What to Remember: Long-horizon Counterfactual Memory Optimization","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}