{"total":82,"rows":[{"id":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221,"area":"mllm"},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2507.13019","title":"Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities","created":"2025-07-17","cited_by_count":25,"area":"lr"},{"id":"2503.01378","title":"CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs","created":"2025-03-03","cited_by_count":22,"area":"lr"},{"id":"2412.05255","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","created":"2024-12-06","cited_by_count":21,"area":null},{"id":"2504.17950","title":"Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning","created":"2025-04-24","cited_by_count":21,"area":"lr"},{"id":"2505.16348","title":"Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization","created":"2025-05-22","cited_by_count":19,"area":"agents"},{"id":"2506.09049","title":"VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning","created":"2025-06-10","cited_by_count":18,"area":"mllm"},{"id":"2502.20490","title":"EgoNormia: Benchmarking Physical Social Norm Understanding","created":"2025-02-27","cited_by_count":13,"area":null},{"id":"2602.11583","title":"The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs","created":"2026-02-12","cited_by_count":10,"area":"agents"},{"id":"2506.09420","title":"A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy","created":"2025-06-11","cited_by_count":9,"area":"agents"},{"id":"2510.02557","title":"Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge","created":"2025-10-02","cited_by_count":8,"area":"agents"},{"id":"2501.01366","title":"ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding","created":"2025-01-02","cited_by_count":7,"area":null},{"id":"2504.14773","title":"PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities","created":"2025-04-21","cited_by_count":7,"area":"agents"},{"id":"2507.05178","title":"CREW-WILDFIRE: Benchmarking Agentic Multi-Agent Collaborations at Scale","created":"2025-07-07","cited_by_count":7,"area":"agents"},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2604.07774","title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2606.05622","title":"AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints","created":"2026-06-04","cited_by_count":7,"area":"agents"},{"id":"2412.04531","title":"MageBench: Bridging Large Multimodal Models to Agents","created":"2024-12-05","cited_by_count":6,"area":"mllm"},{"id":"2504.04040","title":"ADAPT: Actively Discovering and Adapting to Preferences for any Task","created":"2025-04-05","cited_by_count":6,"area":"alignment"},{"id":"2506.04098","title":"TextAtari: 100K Frames Game Playing with Language Agents","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2510.05307","title":"When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2507.17257","title":"Agent Identity Evals: Measuring Agentic Identity","created":"2025-07-23","cited_by_count":5,"area":"agents"},{"id":"2511.17384","title":"IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation","created":"2025-11-21","cited_by_count":5,"area":"lr"},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2606.18847","title":"WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2509.02761","title":"Plan Verification for LLM-Based Embodied Task Completion Agents","created":"2025-09-02","cited_by_count":4,"area":"agents"},{"id":"2605.18431","title":"Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models","created":"2026-05-18","cited_by_count":4,"area":"lr"},{"id":"2412.05313","title":"{\\lambda}: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2504.10030","title":"EmbodiedAgent: A Scalable Hierarchical Approach to Overcome Practical Challenge in Multi-Robot Control","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2505.20503","title":"Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review","created":"2025-05-26","cited_by_count":3,"area":"mllm"},{"id":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2605.09826","title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2606.31966","title":"MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments","created":"2026-06-30","cited_by_count":3,"area":"mllm"},{"id":"2503.12974","title":"Exploring 3D Reasoning-Driven Planning: From Implicit Human Intentions to Route-Aware Activity Planning","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2508.05614","title":"GroundAct: Can LLM Agents Ground Actions in Environmental States?","created":"2025-08-07","cited_by_count":2,"area":"agents"},{"id":"2511.00998","title":"GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies","created":"2025-11-02","cited_by_count":2,"area":"diffusion"},{"id":"2604.11174","title":"EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems","created":"2026-04-13","cited_by_count":2,"area":"agents"},{"id":"2604.16813","title":"PersonalHomeBench: Evaluating Agents in Personalized Smart Homes","created":"2026-04-18","cited_by_count":2,"area":"agents"},{"id":"2606.28182","title":"LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior","created":"2026-06-26","cited_by_count":2,"area":"agents"},{"id":"2607.27180","title":"HumanCLAW: Can Vision-Language Models Act Through a Body?","created":"2026-07-29","cited_by_count":2,"area":"mllm"},{"id":"2609.19801","title":"DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum","created":"2026-09-17","cited_by_count":2,"area":"agents"},{"id":"2609.20056","title":"MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution","created":"2026-09-17","cited_by_count":2,"area":null},{"id":"2412.01348","title":"Hierarchical Object-Oriented POMDP Planning for Object Rearrangement","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2506.21329","title":"Active Inference AI Systems for Scientific Discovery","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2507.06157","title":"Evaluation of Habitat Robotics using Large Language Models","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.05091","title":"ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2601.18733","title":"Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge","created":"2026-01-26","cited_by_count":1,"area":"mllm"},{"id":"2602.16902","title":"LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.19229","title":"NavTrust: Benchmarking Trustworthiness for Embodied Navigation","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2608.01428","title":"When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents","created":"2026-08-02","cited_by_count":1,"area":"agents"},{"id":"2608.18292","title":"GuideFetch: A Task Coordination Framework for Concurrent Navigation and Object Retrieval in Assistive Robot Dogs","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2609.36777","title":"Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2412.00435","title":"Towards Real-time Adaptation of Embodied Agent in Human-Robot Collaboration","created":"2024-11-30","cited_by_count":0,"area":"agents"},{"id":"2602.18812","title":"GenPlanner: From Noise to Plans -- Emergent Reasoning in Flow Matching and Diffusion Models","created":"2026-02-21","cited_by_count":0,"area":"diffusion"},{"id":"2605.12920","title":"Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue","created":"2026-05-13","cited_by_count":0,"area":"wm"},{"id":"2605.13335","title":"Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.18109","title":"TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.01848","title":"RescueBench: Can Embodied Agents Save Lives in the Wild ?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.20946","title":"Scaling Diverse Language Generation for 3D Visual Grounding","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.06534","title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","created":"2026-07-07","cited_by_count":0,"area":"mllm"},{"id":"2607.06691","title":"CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.07021","title":"Learning social norms enhances compatibility in dynamic human-AI coordination","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.13056","title":"HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration","created":"2026-07-05","cited_by_count":0,"area":"vla"},{"id":"2607.18062","title":"UniETP: Unifying Environments for Generalizable Embodied Task Planning","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.05729","title":"Unified Agent: Managing Interactions across Devices","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.28266","title":"CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.07448","title":"FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.18520","title":"AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.23997","title":"RoboTalk: Learning Multi-Robot Communication and Coordination from Multimodal Demonstrations","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.29669","title":"Do World Models Make Better Robots? A Survey of Evaluation Benchmarks for Predictive Embodied Intelligence","created":"2026-08-30","cited_by_count":0,"area":"wm"},{"id":"2609.35916","title":"VehicleArena: A Realistic Urban Environment for Multi-Agent Driving","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.35955","title":"HEIR: Learning Human-Entity Interactions with Functional Roles","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35965","title":"Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39727","title":"OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.02161","title":"DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication","created":"2026-10-01","cited_by_count":0,"area":"mllm"},{"id":"2610.13534","title":"MAGMA-Bench: Evaluating Long-Horizon Embodied Agents under Dynamic Tasks and Execution Failures","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16117","title":"Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.16895","title":"Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}