{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295},{"id":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208},{"id":"2408.08152","title":"DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search","created":"2024-08-15","cited_by_count":197},{"id":"1908.09453","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","created":"2019-08-26","cited_by_count":186},{"id":"2312.17617","title":"Large Language Models for Generative Information Extraction: A Survey","created":"2023-12-29","cited_by_count":185},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169},{"id":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165},{"id":"2006.05990","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","created":"2020-06-10","cited_by_count":162},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111},{"id":"1606.04460","title":"Model-Free Episodic Control","created":"2016-06-14","cited_by_count":102},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88},{"id":"1810.04303","title":"Batch Active Preference-Based Learning of Reward Functions","created":"2018-10-10","cited_by_count":87},{"id":"2306.09200","title":"ChessGPT: Bridging Policy Learning and Language Modeling","created":"2023-06-15","cited_by_count":75},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73},{"id":"2310.00752","title":"TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks","created":"2023-10-01","cited_by_count":70},{"id":"2406.16218","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","created":"2024-06-23","cited_by_count":69},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41},{"id":"2312.06853","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback","created":"2023-12-11","cited_by_count":33},{"id":"2002.01080","title":"Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations","created":"2020-02-04","cited_by_count":32},{"id":"2312.14878","title":"Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning","created":"2023-12-22","cited_by_count":30},{"id":"2309.12482","title":"State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding","created":"2023-09-21","cited_by_count":17},{"id":"2402.07876","title":"Policy Improvement using Language Feedback Models","created":"2024-02-12","cited_by_count":16},{"id":"2206.05275","title":"Spatial-temporal Concept based Explanation of 3D ConvNets","created":"2022-06-09","cited_by_count":12},{"id":"2312.03290","title":"Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym","created":"2023-12-06","cited_by_count":2},{"id":"2402.11792","title":"SInViG: A Self-Evolving Interactive Visual Agent for Human-Robot Interaction","created":"2024-02-19","cited_by_count":2}],"next_cursor":null}