{"list":"other","total":109,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"1904.07272","title":"Introduction to Multi-Armed Bandits","created":"2019-04-15","cited_by_count":481},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"2405.17935","title":"Tool Learning with Large Language Models: A Survey","created":"2024-05-28","cited_by_count":223},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185},{"id":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143},{"id":"2310.19046","title":"Large Language Models as Evolutionary Optimizers","created":"2023-10-29","cited_by_count":124},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91},{"id":"2511.10395","title":"AgentEvolver: Towards Efficient Self-Evolving Agent System","created":"2025-11-13","cited_by_count":85},{"id":"2312.02406","title":"Efficient Online Data Mixing For Language Model Pre-Training","created":"2023-12-05","cited_by_count":77},{"id":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76},{"id":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71},{"id":"2005.10619","title":"A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments","created":"2020-05-19","cited_by_count":62},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45},{"id":"2310.09748","title":"Large Language Model-Aware In-Context Learning for Code Generation","created":"2023-10-15","cited_by_count":43},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39},{"id":"2405.16420","title":"M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions","created":"2024-05-26","cited_by_count":38},{"id":"2406.07115","title":"Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees","created":"2024-06-11","cited_by_count":38},{"id":"2402.09723","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","created":"2024-02-15","cited_by_count":37},{"id":"2405.16122","title":"Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars","created":"2024-05-25","cited_by_count":37},{"id":"2310.05204","title":"Towards Optimizing with Large Language Models","created":"2023-10-08","cited_by_count":35},{"id":"2403.16843","title":"Do LLM Agents Have Regret? A Case Study in Online Learning and Games","created":"2024-03-25","cited_by_count":35},{"id":"2405.17346","title":"Prompt Optimization with Human Feedback","created":"2024-05-27","cited_by_count":35},{"id":"2409.16986","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","created":"2024-09-25","cited_by_count":34},{"id":"2502.02743","title":"LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing","created":"2025-02-04","cited_by_count":34},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33},{"id":"2406.03853","title":"Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism","created":"2024-06-06","cited_by_count":32},{"id":"2312.06185","title":"KnowGPT: Knowledge Graph based Prompting for Large Language Models","created":"2023-12-11","cited_by_count":31},{"id":"2310.02905","title":"Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers","created":"2023-10-02","cited_by_count":30},{"id":"2406.00244","title":"Controlling Large Language Model Agents with Entropic Activation Steering","created":"2024-06-01","cited_by_count":29},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29},{"id":"2412.01572","title":"MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity","created":"2024-12-02","cited_by_count":29},{"id":"2403.07213","title":"Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits","created":"2024-03-11","cited_by_count":27},{"id":"2501.12735","title":"Online Preference Alignment for Language Models via Count-based Exploration","created":"2025-01-22","cited_by_count":26},{"id":"2402.14807","title":"A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health","created":"2024-02-22","cited_by_count":24},{"id":"2508.21141","title":"Adaptive LLM Routing under Budget Constraints","created":"2025-08-28","cited_by_count":24},{"id":"2505.15141","title":"BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms","created":"2025-05-21","cited_by_count":20},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19},{"id":"2406.11256","title":"Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts","created":"2024-06-17","cited_by_count":19},{"id":"2506.17670","title":"Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution","created":"2025-06-21","cited_by_count":19},{"id":"2312.00267","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","created":"2023-12-01","cited_by_count":18},{"id":"2504.20997","title":"Toward Efficient Exploration by Large Language Model Agents","created":"2025-04-29","cited_by_count":17},{"id":"2405.07530","title":"Prompt-based Code Completion via Multi-Retrieval Augmented Generation","created":"2024-05-13","cited_by_count":16},{"id":"2406.12125","title":"Efficient Sequential Decision Making with Large Language Models","created":"2024-06-17","cited_by_count":16},{"id":"2410.06617","title":"Learning Evolving Tools for Large Language Models","created":"2024-10-09","cited_by_count":16},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16},{"id":"2510.07429","title":"Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs","created":"2025-10-08","cited_by_count":15},{"id":"2411.16313","title":"CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning","created":"2024-11-25","cited_by_count":14},{"id":"2402.12621","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","created":"2024-02-20","cited_by_count":13},{"id":"2406.19317","title":"Jump Starting Bandits with LLM-Generated Prior Knowledge","created":"2024-06-27","cited_by_count":12},{"id":"2503.01864","title":"Larger or Smaller Reward Margins to Select Preferences for Alignment?","created":"2025-02-25","cited_by_count":11},{"id":"2009.07899","title":"Comparison Lift: Bandit-based Experimentation System for Online Advertising","created":"2020-09-16","cited_by_count":10},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10},{"id":"2505.19241","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","created":"2025-05-25","cited_by_count":10},{"id":"2310.14526","title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization","created":"2023-10-23","cited_by_count":9},{"id":"2404.02649","title":"On the Importance of Uncertainty in Decision-Making with Large Language Models","created":"2024-04-03","cited_by_count":9},{"id":"2408.12112","title":"Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards","created":"2024-08-22","cited_by_count":9},{"id":"2412.07618","title":"Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs","created":"2024-12-10","cited_by_count":9},{"id":"2503.01163","title":"Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers","created":"2025-03-03","cited_by_count":9},{"id":"2508.12116","title":"DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections","created":"2025-08-16","cited_by_count":9},{"id":"2311.02268","title":"LLMs-augmented Contextual Bandit","created":"2023-11-03","cited_by_count":8},{"id":"2510.13907","title":"LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization","created":"2025-10-14","cited_by_count":8},{"id":"2502.00728","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","created":"2025-02-02","cited_by_count":7},{"id":"2510.20064","title":"Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs","created":"2025-10-22","cited_by_count":7},{"id":"2406.10738","title":"Adaptive Experimentation When You Can't Experiment","created":"2024-06-15","cited_by_count":6},{"id":"2404.16115","title":"Online Personalizing White-box LLMs Generation with Neural Bandits","created":"2024-04-24","cited_by_count":5},{"id":"2205.08295","title":"Semi-Parametric Contextual Bandits with Graph-Laplacian Regularization","created":"2022-05-17","cited_by_count":4},{"id":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3},{"id":"2508.13993","title":"Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization","created":"2025-08-19","cited_by_count":3},{"id":"2509.24701","title":"FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits","created":"2025-09-29","cited_by_count":3},{"id":"2509.24923","title":"When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training","created":"2025-09-29","cited_by_count":3},{"id":"2203.13151","title":"Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking","created":"2022-03-24","cited_by_count":2},{"id":"2407.01887","title":"Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents","created":"2024-07-02","cited_by_count":2}],"next_cursor":"100"}