{"list":"other","total":55,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2406.03243","title":"Llumnix: Dynamic Scheduling for Large Language Model Serving","created":"2024-06-05","cited_by_count":174},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165},{"id":"2401.04925","title":"The Impact of Reasoning Step Length on Large Language Models","created":"2024-01-10","cited_by_count":153},{"id":"2311.03285","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","created":"2023-11-06","cited_by_count":152},{"id":"2305.02309","title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages","created":"2023-05-03","cited_by_count":125},{"id":"2401.11181","title":"Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads","created":"2024-01-20","cited_by_count":121},{"id":"2408.00741","title":"DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency","created":"2024-08-01","cited_by_count":112},{"id":"2403.16971","title":"AIOS: LLM Agent Operating System","created":"2024-03-25","cited_by_count":97},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88},{"id":"2305.13144","title":"Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline","created":"2023-05-22","cited_by_count":86},{"id":"2408.15792","title":"Efficient LLM Scheduling by Learning to Rank","created":"2024-08-28","cited_by_count":85},{"id":"2306.06000","title":"S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput","created":"2023-06-09","cited_by_count":81},{"id":"2404.08509","title":"Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction","created":"2024-04-12","cited_by_count":66},{"id":"2402.01586","title":"TrustAgent: Towards Safe and Trustworthy LLM-based Agents","created":"2024-02-02","cited_by_count":64},{"id":"2404.02015","title":"MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving","created":"2024-04-02","cited_by_count":52},{"id":"2410.02223","title":"EmbedLLM: Learning Compact Representations of Large Language Models","created":"2024-10-03","cited_by_count":48},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39},{"id":"2407.18957","title":"When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments","created":"2024-07-15","cited_by_count":26},{"id":"2502.17282","title":"Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing","created":"2025-02-24","cited_by_count":25},{"id":"2502.14662","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","created":"2025-02-20","cited_by_count":23},{"id":"2406.02787","title":"Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities","created":"2024-06-04","cited_by_count":22},{"id":"2311.04590","title":"Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptions","created":"2023-11-08","cited_by_count":20},{"id":"2406.04785","title":"Enabling Efficient Batch Serving for LMaaS via Generation Length Prediction","created":"2024-06-07","cited_by_count":20},{"id":"2401.16553","title":"SelectLLM: Can LLMs Select Important Instructions to Annotate?","created":"2024-01-29","cited_by_count":16},{"id":"2410.10456","title":"Ada-K Routing: Boosting the Efficiency of MoE-based LLMs","created":"2024-10-14","cited_by_count":16},{"id":"2410.11843","title":"From Commands to Prompts: LLM-based Semantic File System for AIOS","created":"2024-09-23","cited_by_count":14},{"id":"1802.04874","title":"GILBO: One Metric to Measure Them All","created":"2018-02-13","cited_by_count":9},{"id":"2302.05919","title":"Neural Node Matching for Multi-Target Cross Domain Recommendation","created":"2023-02-12","cited_by_count":8},{"id":"2310.17488","title":"LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation","created":"2023-10-26","cited_by_count":8},{"id":"2002.00352","title":"Solving Billion-Scale Knapsack Problems","created":"2020-02-02","cited_by_count":3}],"next_cursor":null}