{"total":55,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695,"area":"lr"},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395,"area":"agents"},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162,"area":null},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142,"area":"offlinerl"},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142,"area":"mllm"},{"id":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125,"area":"agents"},{"id":"2204.03514","title":"Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale","created":"2022-04-07","cited_by_count":117,"area":"offlinerl"},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111,"area":"agents"},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71,"area":null},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69,"area":null},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68,"area":null},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","cited_by_count":58,"area":null},{"id":"2204.05080","title":"Semantic Exploration from Language Abstractions and Pretrained Representations","created":"2022-04-08","cited_by_count":51,"area":null},{"id":"2107.12514","title":"Language Grounding with 3D Objects","created":"2021-07-26","cited_by_count":43,"area":null},{"id":"2401.10568","title":"CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents","created":"2024-01-19","cited_by_count":42,"area":"lr"},{"id":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"area":null},{"id":"2401.05345","title":"DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelines","created":"2023-12-01","cited_by_count":36,"area":null},{"id":"2401.14151","title":"True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning","created":"2024-01-25","cited_by_count":36,"area":null},{"id":"2304.10750","title":"Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback","created":"2023-04-21","cited_by_count":32,"area":null},{"id":"2411.00986","title":"Taking AI Welfare Seriously","created":"2024-11-04","cited_by_count":31,"area":"agents"},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"area":"agents"},{"id":"2301.12507","title":"Distilling Internet-Scale Vision-Language Models into Embodied Agents","created":"2023-01-29","cited_by_count":30,"area":"mllm"},{"id":"2211.11602","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","created":"2022-11-21","cited_by_count":26,"area":"alignment"},{"id":"2102.03406","title":"Symbolic Behaviour in Artificial Intelligence","created":"2021-02-05","cited_by_count":25,"area":null},{"id":"2106.13871","title":"Transflower: probabilistic autoregressive dance generation with multimodal attention","created":"2021-06-25","cited_by_count":22,"area":null},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19,"area":null},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2205.13771","title":"IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022","created":"2022-05-27","cited_by_count":14,"area":null},{"id":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"id":"2305.10783","title":"Transforming Human-Centered AI Collaboration: Redefining Embodied Agents Capabilities through Interactive Grounded Language Instructions","created":"2023-05-18","cited_by_count":13,"area":null},{"id":"2310.15940","title":"Combining Behaviors with the Successor Features Keyboard","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2404.18243","title":"LEGENT: Open Platform for Embodied Agents","created":"2024-04-28","cited_by_count":12,"area":"wm"},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2211.06552","title":"Collecting Interactive Multi-modal Datasets for Grounded Language Understanding","created":"2022-11-12","cited_by_count":10,"area":null},{"id":"2407.15134","title":"Proximal Policy Distillation","created":"2024-07-21","cited_by_count":9,"area":"distill"},{"id":"2412.10410","title":"GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents","created":"2024-12-07","cited_by_count":9,"area":null},{"id":"2107.00956","title":"SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-07-02","cited_by_count":7,"area":null},{"id":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2205.13274","title":"Evaluating Multimodal Interactive Agents","created":"2022-05-26","cited_by_count":5,"area":null},{"id":"2105.10577","title":"Modelling the development of counting with memory-augmented neural networks","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2201.11441","title":"Human-centered mechanism design with Democratic AI","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2309.11564","title":"Hierarchical reinforcement learning with natural language subgoals","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2401.08585","title":"From Conceptual Spaces to Quantum Concepts: Formalising and Learning Structured Conceptual Models","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2509.08500","title":"TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making","created":"2025-09-10","cited_by_count":3,"area":"lr"},{"id":"2104.13207","title":"SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-04-27","cited_by_count":1,"area":null},{"id":"2207.07437","title":"Learning Flexible Translation between Robot Actions and Language Descriptions","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2407.08898","title":"IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving Agents","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2301.03353","title":"Learning Bidirectional Action-Language Translation with Limited Supervision and Incongruent Input","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2308.02514","title":"Language models as master equation solvers","created":"2023-07-29","cited_by_count":0,"area":null}],"next_cursor":null}