{"list":"other","total":53,"rows":[{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830},{"id":"2504.19413","title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","created":"2025-04-28","cited_by_count":779},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2510.04618","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","created":"2025-10-06","cited_by_count":398},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"id":"2401.15391","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","created":"2024-01-27","cited_by_count":257},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246},{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206},{"id":"2510.05381","title":"Context Length Alone Hurts LLM Performance Despite Perfect Retrieval","created":"2025-10-06","cited_by_count":127},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126},{"id":"2510.09665","title":"LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference","created":"2025-10-08","cited_by_count":126},{"id":"2402.17453","title":"DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning","created":"2024-02-27","cited_by_count":125},{"id":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123},{"id":"2407.16833","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","created":"2024-07-23","cited_by_count":119},{"id":"2212.04458","title":"General-Purpose In-Context Learning by Meta-Learning Transformers","created":"2022-12-08","cited_by_count":105},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98},{"id":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95},{"id":"2404.08189","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","created":"2024-04-12","cited_by_count":93},{"id":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87},{"id":"2401.14351","title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models","created":"2024-01-25","cited_by_count":80},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66},{"id":"2410.04343","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","created":"2024-10-06","cited_by_count":65},{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","cited_by_count":63},{"id":"2503.11951","title":"SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning","created":"2025-03-15","cited_by_count":60},{"id":"2509.22819","title":"Hilbert: Recursively Building Formal Proofs with Informal Reasoning","created":"2025-09-26","cited_by_count":60},{"id":"2501.03468","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","created":"2025-01-07","cited_by_count":51},{"id":"2506.06698","title":"Contextual Experience Replay for Self-Improvement of Language Agents","created":"2025-06-07","cited_by_count":48},{"id":"2411.02886","title":"TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection","created":"2024-11-05","cited_by_count":39},{"id":"2409.15355","title":"Block-Attention for Efficient Prefilling","created":"2024-09-14","cited_by_count":37},{"id":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36},{"id":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31},{"id":"2501.12372","title":"Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL","created":"2025-01-21","cited_by_count":30},{"id":"2502.05431","title":"APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding","created":"2025-02-08","cited_by_count":29},{"id":"2508.18572","title":"Strata: Hierarchical Context Caching for Long Context Language Model Serving","created":"2025-08-26","cited_by_count":26},{"id":"2310.09949","title":"Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models","created":"2023-10-15","cited_by_count":23},{"id":"2409.12558","title":"RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues","created":"2024-09-19","cited_by_count":19},{"id":"2510.26493","title":"Context Engineering 2.0: The Context of Context Engineering","created":"2025-10-30","cited_by_count":18},{"id":"2505.21700","title":"Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis","created":"2025-05-27","cited_by_count":17},{"id":"2502.20330","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","created":"2025-02-27","cited_by_count":14},{"id":"2502.04563","title":"WaferLLM: Large Language Model Inference at Wafer Scale","created":"2025-02-06","cited_by_count":13},{"id":"2505.11415","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2025-05-16","cited_by_count":11},{"id":"2312.16159","title":"Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages","created":"2023-12-26","cited_by_count":8},{"id":"2503.18773","title":"BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache","created":"2025-03-24","cited_by_count":8},{"id":"2504.02921","title":"HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse","created":"2025-04-03","cited_by_count":8},{"id":"2509.10886","title":"CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis","created":"2025-09-13","cited_by_count":6}],"next_cursor":null}