{"list":"other","total":51,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"2506.03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval","created":"2025-06-03","cited_by_count":163},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"2309.10062","title":"SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models","created":"2023-09-18","cited_by_count":153},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"2406.17294","title":"Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models","created":"2024-06-25","cited_by_count":133},{"id":"2501.08325","title":"GameFactory: Creating New Games with Generative Interactive Videos","created":"2025-01-14","cited_by_count":130},{"id":"2407.08739","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","created":"2024-07-11","cited_by_count":113},{"id":"2403.12482","title":"Embodied LLM Agents Learn to Cooperate in Organized Teams","created":"2024-03-19","cited_by_count":82},{"id":"2411.00081","title":"PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks","created":"2024-10-31","cited_by_count":82},{"id":"2310.03903","title":"LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models","created":"2023-10-05","cited_by_count":68},{"id":"2312.07472","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","created":"2023-12-12","cited_by_count":67},{"id":"2412.04455","title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","created":"2024-12-05","cited_by_count":63},{"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":"2007.04979","title":"A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks","created":"2020-07-09","cited_by_count":52},{"id":"2404.10775","title":"COMBO: Compositional World Models for Embodied Multi-Agent Cooperation","created":"2024-04-16","cited_by_count":49},{"id":"2310.13255","title":"Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds","created":"2023-10-20","cited_by_count":45},{"id":"2407.10031","title":"LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments","created":"2024-07-14","cited_by_count":32},{"id":"2503.02390","title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","created":"2025-03-04","cited_by_count":31},{"id":"2503.16408","title":"RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints","created":"2025-03-20","cited_by_count":31},{"id":"2410.21040","title":"LiP-LLM: Integrating Linear Programming and dependency graph with Large Language Models for multi-robot task planning","created":"2024-10-28","cited_by_count":24},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23},{"id":"2411.09022","title":"DART-LLM: Dependency-Aware Multi-Robot Task Decomposition and Execution using Large Language Models","created":"2024-11-13","cited_by_count":19},{"id":"2503.13861","title":"RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous Driving","created":"2025-03-18","cited_by_count":18},{"id":"2505.22634","title":"LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents","created":"2025-05-28","cited_by_count":15},{"id":"2410.24152","title":"Language-Driven Policy Distillation for Cooperative Driving in Multi-Agent Reinforcement Learning","created":"2024-10-31","cited_by_count":14},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13},{"id":"2502.13894","title":"NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants","created":"2025-02-19","cited_by_count":11},{"id":"2109.09531","title":"Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge","created":"2021-09-20","cited_by_count":10},{"id":"2503.09758","title":"Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation","created":"2025-03-12","cited_by_count":8},{"id":"2505.17050","title":"Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning","created":"2025-05-16","cited_by_count":7}],"next_cursor":null}