{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2304.11477","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","created":"2023-04-22","cited_by_count":501},{"id":"2306.15626","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","created":"2023-06-27","cited_by_count":427},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"2305.16653","title":"AdaPlanner: Adaptive Planning from Feedback with Language Models","created":"2023-05-26","cited_by_count":196},{"id":"1705.07798","title":"A unified view of entropy-regularized Markov decision processes","created":"2017-05-22","cited_by_count":182},{"id":"2305.11014","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","created":"2023-05-18","cited_by_count":139},{"id":"1906.07343","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","created":"2019-06-18","cited_by_count":138},{"id":"2302.05128","title":"Translating Natural Language to Planning Goals with Large-Language Models","created":"2023-02-10","cited_by_count":133},{"id":"2310.08118","title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?","created":"2023-10-12","cited_by_count":108},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"id":"2308.04371","title":"Cumulative Reasoning with Large Language Models","created":"2023-08-08","cited_by_count":94},{"id":"2007.13442","title":"Fast active learning for pure exploration in reinforcement learning","created":"2020-07-27","cited_by_count":92},{"id":"2308.10379","title":"Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models","created":"2023-08-20","cited_by_count":92},{"id":"2302.06706","title":"On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)","created":"2023-02-13","cited_by_count":85},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"2401.02009","title":"Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives","created":"2024-01-04","cited_by_count":71},{"id":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","cited_by_count":58},{"id":"2106.00188","title":"PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World","created":"2021-06-01","cited_by_count":47},{"id":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46},{"id":"2305.16151","title":"Understanding the Capabilities of Large Language Models for Automated Planning","created":"2023-05-25","cited_by_count":34},{"id":"2109.14830","title":"Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators","created":"2021-09-30","cited_by_count":21},{"id":"2305.15695","title":"Asking Before Acting: Gather Information in Embodied Decision Making with Language Models","created":"2023-05-25","cited_by_count":12},{"id":"2304.11063","title":"Think Before You Act: Unified Policy for Interleaving Language Reasoning with Actions","created":"2023-04-18","cited_by_count":8},{"id":"2306.12554","title":"Improving Long-Horizon Imitation Through Instruction Prediction","created":"2023-06-21","cited_by_count":8},{"id":"2312.01276","title":"Toward best research practices in AI Psychology","created":"2023-12-03","cited_by_count":8},{"id":"2310.19927","title":"Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms","created":"2023-10-30","cited_by_count":7},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5}],"next_cursor":null}