{"list":"other","total":56,"rows":[{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"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":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2305.00447","title":"TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation","created":"2023-04-30","cited_by_count":337},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"2502.14768","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","created":"2025-02-20","cited_by_count":262},{"id":"2011.07876","title":"A Survey on the Explainability of Supervised Machine Learning","created":"2020-11-16","cited_by_count":227},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2010.02840","title":"Semantic Evaluation for Text-to-SQL with Distilled Test Suites","created":"2020-10-06","cited_by_count":126},{"id":"2305.06474","title":"Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction","created":"2023-05-10","cited_by_count":116},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"2011.09607","title":"FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance","created":"2020-11-19","cited_by_count":87},{"id":"2307.15780","title":"LLM-Rec: Personalized Recommendation via Prompting Large Language Models","created":"2023-07-24","cited_by_count":77},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71},{"id":"2403.03230","title":"Large language models surpass human experts in predicting neuroscience results","created":"2024-03-04","cited_by_count":69},{"id":"2204.01959","title":"Data Augmentation for Intent Classification with Off-the-shelf Large Language Models","created":"2022-04-05","cited_by_count":49},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45},{"id":"1805.09461","title":"Deep Reinforcement Learning For Sequence to Sequence Models","created":"2018-05-24","cited_by_count":39},{"id":"2310.07984","title":"Large Language Models for Scientific Synthesis, Inference and Explanation","created":"2023-10-12","cited_by_count":39},{"id":"2101.00297","title":"Analyzing Commonsense Emergence in Few-shot Knowledge Models","created":"2021-01-01","cited_by_count":34},{"id":"2403.02990","title":"Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges","created":"2024-03-05","cited_by_count":30},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26},{"id":"2407.06025","title":"iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement","created":"2024-07-08","cited_by_count":23},{"id":"2401.07382","title":"Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation","created":"2024-01-14","cited_by_count":22},{"id":"2408.06276","title":"Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation","created":"2024-08-12","cited_by_count":22},{"id":"2403.09583","title":"ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models","created":"2024-03-14","cited_by_count":19},{"id":"2202.09662","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","created":"2022-02-19","cited_by_count":18},{"id":"2401.03506","title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","created":"2024-01-07","cited_by_count":16},{"id":"2407.08462","title":"Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computing","created":"2024-07-11","cited_by_count":15},{"id":"2402.16181","title":"How Can LLM Guide RL? A Value-Based Approach","created":"2024-02-25","cited_by_count":13},{"id":"2310.07611","title":"Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models","created":"2023-10-11","cited_by_count":11},{"id":"2406.07857","title":"Toward Enhanced Reinforcement Learning-Based Resource Management via Digital Twin: Opportunities, Applications, and Challenges","created":"2024-06-12","cited_by_count":10},{"id":"2311.05596","title":"LLM Augmented Hierarchical Agents","created":"2023-11-09","cited_by_count":9},{"id":"2411.06463","title":"RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration","created":"2024-11-10","cited_by_count":9},{"id":"2504.03622","title":"Align to Structure: Aligning Large Language Models with Structural Information","created":"2025-04-04","cited_by_count":6},{"id":"1806.05310","title":"Deep Reinforcement Learning for Dynamic Urban Transportation Problems","created":"2018-06-14","cited_by_count":5},{"id":"2307.07047","title":"Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?","created":"2023-07-13","cited_by_count":5},{"id":"2002.11523","title":"Using Reinforcement Learning in the Algorithmic Trading Problem","created":"2020-02-26","cited_by_count":4},{"id":"2404.18978","title":"Towards Generalizable Agents in Text-Based Educational Environments: A Study of Integrating RL with LLMs","created":"2024-04-29","cited_by_count":4},{"id":"2408.01063","title":"Leveraging Encoder-only Large Language Models for Mobile App Review Feature Extraction","created":"2024-08-02","cited_by_count":3},{"id":"2502.10299","title":"Open-Source AI-Powered Optimization in Scalene: Advancing Python Performance Profiling with DeepSeek-R1 and LLaMA 3.2","created":"2025-02-14","cited_by_count":2},{"id":"2501.17752","title":"On the Partitioning of GPU Power among Multi-Instances","created":"2025-01-29","cited_by_count":1}],"next_cursor":null}