{"total":67,"rows":[{"id":"2510.18866","title":"LightMem: Lightweight and Efficient Memory-Augmented Generation","created":"2025-10-21","cited_by_count":180,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2510.06727","title":"Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management","created":"2025-10-08","cited_by_count":51,"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":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39,"area":null},{"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":"2603.29919","title":"SkillReducer: Optimizing LLM Agent Skills for Token Efficiency","created":"2026-03-31","cited_by_count":33,"area":"agents"},{"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":"2505.10413","title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","created":"2025-05-15","cited_by_count":16,"area":"rag"},{"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":"2410.13846","title":"LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation","created":"2024-10-17","cited_by_count":12,"area":"lr"},{"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":"2507.22931","title":"Enhancing RAG Efficiency with Adaptive Context Compression","created":"2025-07-24","cited_by_count":8,"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":"2507.06085","title":"A Survey on Prompt Tuning","created":"2025-07-08","cited_by_count":7,"area":null},{"id":"2503.03979","title":"ReasonGraph: Visualisation of Reasoning Paths","created":"2025-03-06","cited_by_count":6,"area":"lr"},{"id":"2505.09519","title":"PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning","created":"2025-05-14","cited_by_count":6,"area":"moe"},{"id":"2506.15001","title":"Memory Tokens: Large Language Models Can Generate Reversible Sentence Embeddings","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2505.11271","title":"Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models","created":"2025-05-16","cited_by_count":5,"area":"rag"},{"id":"2510.09404","title":"Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges","created":"2025-10-10","cited_by_count":5,"area":"agents"},{"id":"2601.05062","title":"Compositional Steering of Large Language Models with Steering Tokens","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2504.16786","title":"MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores","created":"2025-04-23","cited_by_count":4,"area":null},{"id":"2506.00307","title":"Lossless Token Sequence Compression via Meta-Tokens","created":"2025-05-30","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":"2602.05883","title":"A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges","created":"2026-02-05","cited_by_count":3,"area":null},{"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":"2605.17304","title":"Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression","created":"2026-05-17","cited_by_count":3,"area":"inference"},{"id":"2605.21463","title":"Mem-$\\pi$: Adaptive Memory through Learning When and What to Generate","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2606.31650","title":"ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL","created":"2026-06-30","cited_by_count":3,"area":"agents"},{"id":"2509.20820","title":"Distilling Many-Shot In-Context Learning into a Cheat Sheet","created":"2025-09-25","cited_by_count":2,"area":null},{"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":"2512.01949","title":"Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models","created":"2025-12-01","cited_by_count":2,"area":"mllm"},{"id":"2512.16970","title":"PAACE: A Plan-Aware Automated Agent Context Engineering Framework","created":"2025-12-18","cited_by_count":2,"area":"agents"},{"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":"2603.07777","title":"Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"id":"2603.23527","title":"Compression Method Matters: Benchmark-Dependent Output Dynamics in LLM Prompt Compression","created":"2026-03-06","cited_by_count":2,"area":"inference"},{"id":"2604.11045","title":"Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2607.14275","title":"AI Agents Do Not Fail Alone:The Context Fails First","created":"2026-07-15","cited_by_count":2,"area":"agents"},{"id":"2511.12281","title":"Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor","created":"2025-11-15","cited_by_count":1,"area":"inference"},{"id":"2511.16846","title":"ConCISE: A Reference-Free Conciseness Evaluation Metric for LLM-Generated Answers","created":"2025-11-20","cited_by_count":1,"area":null},{"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":"2602.13980","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":"2603.19987","title":"Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2604.06627","title":"DiffuMask: Diffusion Language Model for Token-level Prompt Pruning","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2605.22641","title":"More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.18406","title":"CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2606.21807","title":"Fixed RAG Compression Collapses Measured Reader Scaling","created":"2026-06-20","cited_by_count":1,"area":"rag"},{"id":"2608.26175","title":"Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors","created":"2026-07-27","cited_by_count":1,"area":"inference"},{"id":"2509.26415","title":"Automatic Fact-checking in English and Telugu","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2601.13481","title":"Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement","created":"2026-01-20","cited_by_count":0,"area":"agents"},{"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":"2605.05974","title":"PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2605.09100","title":"GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression","created":"2026-05-09","cited_by_count":0,"area":"lr"},{"id":"2606.03768","title":"HybridThinker: Efficient Chain-of-Thought Reasoning via Compressed Memory and Transient Thought Steps","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.20571","title":"Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices","created":"2026-04-27","cited_by_count":0,"area":"rag"},{"id":"2606.24083","title":"CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.24791","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","created":"2026-06-28","cited_by_count":0,"area":"rag"},{"id":"2608.08630","title":"VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling","created":"2026-08-09","cited_by_count":0,"area":"mllm"},{"id":"2608.19535","title":"From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG","created":"2026-08-20","cited_by_count":0,"area":"rag"},{"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":"2609.27380","title":"MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression","created":"2026-09-23","cited_by_count":0,"area":"rag"},{"id":"2609.32302","title":"On the Capability and Limitation of Hard Prompt","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36435","title":"MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02736","title":"TPBench: A Turning-Point Benchmark for Dialogue Compression","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}