{"list":"other","total":63,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"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":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"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":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"2304.09542","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","created":"2023-04-19","cited_by_count":360},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267},{"id":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"id":"2309.04658","title":"Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf","created":"2023-09-09","cited_by_count":241},{"id":"2210.02928","title":"MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text","created":"2022-10-06","cited_by_count":220},{"id":"2306.07863","title":"Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control","created":"2023-06-13","cited_by_count":187},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"2311.17136","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","created":"2023-11-28","cited_by_count":166},{"id":"2111.03043","title":"A System for General In-Hand Object Re-Orientation","created":"2021-11-04","cited_by_count":165},{"id":"2303.00905","title":"Open-World Object Manipulation using Pre-trained Vision-Language Models","created":"2023-03-02","cited_by_count":156},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117},{"id":"2309.11382","title":"Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions","created":"2023-09-20","cited_by_count":110},{"id":"2308.11339","title":"ProAgent: Building Proactive Cooperative Agents with Large Language Models","created":"2023-08-22","cited_by_count":98},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97},{"id":"2309.17234","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","created":"2023-09-29","cited_by_count":96},{"id":"2308.04026","title":"AgentSims: An Open-Source Sandbox for Large Language Model Evaluation","created":"2023-08-08","cited_by_count":88},{"id":"2408.03615","title":"Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks","created":"2024-08-07","cited_by_count":84},{"id":"2402.03610","title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents","created":"2024-02-06","cited_by_count":80},{"id":"2310.05418","title":"Humanoid Agents: Platform for Simulating Human-like Generative Agents","created":"2023-10-09","cited_by_count":73},{"id":"2403.12037","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","created":"2024-03-18","cited_by_count":53},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51},{"id":"2310.02172","title":"Lyfe Agents: Generative agents for low-cost real-time social interactions","created":"2023-10-03","cited_by_count":49},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42},{"id":"2407.03913","title":"MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices","created":"2024-07-04","cited_by_count":29},{"id":"2402.04578","title":"S-Agents: Self-organizing Agents in Open-ended Environments","created":"2024-02-07","cited_by_count":22},{"id":"2311.01555","title":"Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers","created":"2023-11-02","cited_by_count":19},{"id":"2403.00690","title":"Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents","created":"2024-03-01","cited_by_count":17},{"id":"2407.18550","title":"ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments","created":"2024-07-26","cited_by_count":16},{"id":"2409.11279","title":"P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task","created":"2024-09-17","cited_by_count":15},{"id":"2303.10571","title":"Reinforcement Learning Friendly Vision-Language Model for Minecraft","created":"2023-03-19","cited_by_count":14},{"id":"2102.04980","title":"Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval","created":"2021-02-09","cited_by_count":12}],"next_cursor":null}