{"total":55,"rows":[{"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":"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":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47,"area":null},{"id":"2501.00332","title":"MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation","created":"2024-12-31","cited_by_count":44,"area":"rag"},{"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":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"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":"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":"2405.03085","title":"Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation","created":"2024-05-06","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":"2502.00258","title":"ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs","created":"2025-02-01","cited_by_count":11,"area":null},{"id":"2509.16330","title":"Generalizability of Large Language Model-Based Agents: A Comprehensive Survey","created":"2025-09-19","cited_by_count":10,"area":"agents"},{"id":"2510.16932","title":"Prompt-MII: Meta-Learning Instruction Induction for LLMs","created":"2025-10-19","cited_by_count":9,"area":null},{"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":"2410.15252","title":"Lossless KV Cache Compression to 2%","created":"2024-10-20","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":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2510.20797","title":"No Mean Feat: Simple, Strong Baselines for Context Compression","created":"2025-10-23","cited_by_count":7,"area":"inference"},{"id":"2404.12283","title":"Enhancing Embedding Performance through Large Language Model-based Text Enrichment and Rewriting","created":"2024-04-18","cited_by_count":6,"area":null},{"id":"2409.15395","title":"Parse Trees Guided LLM Prompt Compression","created":"2024-09-23","cited_by_count":6,"area":"inference"},{"id":"2508.02053","title":"ProCut: LLM Prompt Compression via Attribution Estimation","created":"2025-08-04","cited_by_count":6,"area":"inference"},{"id":"2602.01766","title":"CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2602.24287","title":"Do LLMs Benefit From Their Own Words?","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2506.00307","title":"Lossless Token Sequence Compression via Meta-Tokens","created":"2025-05-30","cited_by_count":4,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2510.22101","title":"Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2601.09703","title":"ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation","created":"2026-01-14","cited_by_count":3,"area":"inference"},{"id":"2602.02366","title":"ReasonCACHE: Teaching LLMs To Reason Without Weight Updates","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2502.10634","title":"Lost in the Passage: Passage-level In-context Learning Does Not Necessarily Need a \"Passage\"","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2508.17032","title":"Learned Structure in Cartridges: Keys as Shareable Routers in Self-Studied Representations","created":"2025-08-23","cited_by_count":2,"area":"inference"},{"id":"2510.09474","title":"Multimodal Policy Internalization for Conversational Agents","created":"2025-10-10","cited_by_count":2,"area":"agents"},{"id":"2510.11588","title":"Analyzing and Internalizing Complex Policy Documents for LLM Agents","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2510.18043","title":"CompactPrompt: A Unified Pipeline for Prompt Data Compression in LLM Workflows","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2601.05589","title":"ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2608.01672","title":"Learning What to Remember: Test-Time Training via Context Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2510.16439","title":"FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2511.12281","title":"Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor","created":"2025-11-15","cited_by_count":1,"area":"inference"},{"id":"2512.03643","title":"Optical Context Compression Is Just (Bad) Autoencoding","created":"2025-12-03","cited_by_count":1,"area":"inference"},{"id":"2602.03216","title":"Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection","created":"2026-02-03","cited_by_count":1,"area":null},{"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":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.19857","title":"Large Language Models Do Not Always Need Readable Language","created":"2026-06-18","cited_by_count":1,"area":null},{"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":"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":"2603.23989","title":"CoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context Reconstruction","created":"2026-03-25","cited_by_count":0,"area":"rag"},{"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"},{"id":"2607.25335","title":"Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors","created":"2026-07-28","cited_by_count":0,"area":"inference"},{"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":"2609.27233","title":"Distilling Sequential Computation in Transformer Language Models","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31505","title":"Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32474","title":"PC-SubMax: Efficient Prompt Compression via Regularized Submodular Maximization","created":"2026-09-26","cited_by_count":0,"area":"inference"}],"next_cursor":null}