{"total":58,"rows":[{"id":"2506.18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","created":"2025-06-22","cited_by_count":518,"area":null},{"id":"2504.13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins","created":"2025-04-17","cited_by_count":121,"area":null},{"id":"2411.19309","title":"GRAPE: Generalizing Robot Policy via Preference Alignment","created":"2024-11-28","cited_by_count":109,"area":"vla"},{"id":"2408.09559","title":"HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model","created":"2024-08-18","cited_by_count":106,"area":"lr"},{"id":"2603.22435","title":"CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation","created":"2026-03-23","cited_by_count":88,"area":"vla"},{"id":"2408.00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","created":"2024-08-01","cited_by_count":83,"area":"lr"},{"id":"2409.02920","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)","created":"2024-09-04","cited_by_count":69,"area":null},{"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,"area":null},{"id":"2607.00272","title":"ASPIRE: Agentic /Skills Discovery for Robotics","created":"2026-06-30","cited_by_count":53,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2607.08448","title":"Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents","created":"2026-07-09","cited_by_count":47,"area":"agents"},{"id":"2409.14411","title":"Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation","created":"2024-09-22","cited_by_count":38,"area":"diffusion"},{"id":"2505.11935","title":"ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing","created":"2025-05-17","cited_by_count":32,"area":"mllm"},{"id":"2502.13092","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation","created":"2025-02-18","cited_by_count":26,"area":"wm"},{"id":"2410.22662","title":"EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents","created":"2024-10-30","cited_by_count":24,"area":"agents"},{"id":"2606.19419","title":"Playful Agentic Robot Learning","created":"2026-06-17","cited_by_count":22,"area":"agents"},{"id":"2506.20966","title":"Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends","created":"2025-06-26","cited_by_count":17,"area":"mllm"},{"id":"2411.18562","title":"DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation","created":"2024-11-27","cited_by_count":15,"area":null},{"id":"2510.23564","title":"ReCode: Unify Plan and Action for Universal Granularity Control","created":"2025-10-27","cited_by_count":15,"area":null},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2406.09953","title":"DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planning","created":"2024-06-14","cited_by_count":14,"area":null},{"id":"2501.04268","title":"Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation","created":"2025-01-08","cited_by_count":11,"area":"lr"},{"id":"2510.21302","title":"Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning","created":"2025-10-24","cited_by_count":11,"area":null},{"id":"2603.02623","title":"Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation","created":"2026-03-03","cited_by_count":9,"area":"synth"},{"id":"2410.20927","title":"VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions","created":"2024-10-28","cited_by_count":8,"area":"mllm"},{"id":"2609.12541","title":"Agent as Policy for Robotic Manipulation","created":"2026-09-11","cited_by_count":8,"area":null},{"id":"2407.06951","title":"RoboCAS: A Benchmark for Robotic Manipulation in Complex Object Arrangement Scenarios","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2509.18597","title":"Growing with Your Embodied Agent: A Human-in-the-Loop Lifelong Code Generation Framework for Long-Horizon Manipulation Skills","created":"2025-09-23","cited_by_count":7,"area":"agents"},{"id":"2608.03924","title":"ETA: A New Agentic Paradigm for Embodied Tasks","created":"2026-08-04","cited_by_count":7,"area":"agents"},{"id":"2410.17337","title":"Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data","created":"2024-10-22","cited_by_count":6,"area":null},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2510.05213","title":"VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2403.13801","title":"Natural Language as Policies: Reasoning for Coordinate-Level Embodied Control with LLMs","created":"2024-03-20","cited_by_count":4,"area":"lr"},{"id":"2407.15819","title":"Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight","created":"2024-07-22","cited_by_count":4,"area":"mllm"},{"id":"2506.14763","title":"RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills","created":"2025-06-17","cited_by_count":4,"area":"agents"},{"id":"2609.27308","title":"EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics","created":"2026-09-23","cited_by_count":4,"area":"agents"},{"id":"2409.10027","title":"E2Map: Experience-and-Emotion Map for Self-Reflective Robot Navigation with Language Models","created":"2024-09-16","cited_by_count":3,"area":null},{"id":"2410.17602","title":"Integrating Large Language Models for UAV Control in Simulated Environments: A Modular Interaction Approach","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2503.21969","title":"Robotic Long-Horizon Manipulation with Progressive In-Context Code Generation and Episodic Feedback","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2507.08719","title":"Multilingual Multimodal Software Developer for Code Generation","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2510.06207","title":"EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model","created":"2025-10-07","cited_by_count":3,"area":"vla"},{"id":"2603.13925","title":"SmoothVLA: Aligning Vision-Language-Action Models with Physical Constraints via Intrinsic Smoothness Optimization","created":"2026-03-14","cited_by_count":3,"area":"vla"},{"id":"2609.20822","title":"Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2409.11041","title":"Towards No-Code Programming of Cobots: Experiments with Code Synthesis by Large Code Models for Conversational Programming","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2506.06683","title":"RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2508.02629","title":"HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents","created":"2025-08-04","cited_by_count":2,"area":"mllm"},{"id":"2609.29964","title":"World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal","created":"2026-09-24","cited_by_count":2,"area":"lr"},{"id":"2609.38982","title":"SimEX: Simulation-Integrated Robotics AutoResearch","created":"2026-09-30","cited_by_count":2,"area":"agents"},{"id":"2505.06402","title":"Camera Control at the Edge with Language Models for Scene Understanding","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.14047","title":"Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use","created":"2026-08-14","cited_by_count":1,"area":"vla"},{"id":"2609.35432","title":"Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence","created":"2026-09-28","cited_by_count":1,"area":"vla"},{"id":"2511.19315","title":"Rethinking Intermediate Representation for VLM-based Robot Manipulation","created":"2025-11-24","cited_by_count":0,"area":"lr"},{"id":"2603.16809","title":"CABTO: Context-Aware Behavior Tree Grounding for Robot Manipulation","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.07999","title":"Efficient Skill Grounding via Code Refactoring with Small Language Models","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.13097","title":"Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2610.12549","title":"Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.18874","title":"ChunkAct: Action Chunking for Agentic Robotics","created":"2026-10-13","cited_by_count":0,"area":"vla"}],"next_cursor":null}