{"list":"other","total":116,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"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":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"1806.11532","title":"TextWorld: A Learning Environment for Text-based Games","created":"2018-06-29","cited_by_count":310},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"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},{"id":"2502.19417","title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","created":"2025-02-26","cited_by_count":221},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208},{"id":"2403.02502","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","created":"2024-03-04","cited_by_count":197},{"id":"2503.09572","title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","created":"2025-03-12","cited_by_count":195},{"id":"2503.15558","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","created":"2025-03-18","cited_by_count":164},{"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":"2212.00193","title":"Distilling Reasoning Capabilities into Smaller Language Models","created":"2022-12-01","cited_by_count":158},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158},{"id":"2502.21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","created":"2025-02-28","cited_by_count":135},{"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":"2110.07342","title":"FILM: Following Instructions in Language with Modular Methods","created":"2021-10-12","cited_by_count":121},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103},{"id":"2507.02029","title":"RoboBrain 2.0 Technical Report","created":"2025-07-02","cited_by_count":89},{"id":"2406.11176","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","created":"2024-06-17","cited_by_count":88},{"id":"2510.03342","title":"Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer","created":"2025-10-02","cited_by_count":87},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86},{"id":"2307.01848","title":"Embodied Task Planning with Large Language Models","created":"2023-07-04","cited_by_count":84},{"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":"2501.11425","title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training","created":"2025-01-20","cited_by_count":82},{"id":"2510.21618","title":"DeepAgent: A General Reasoning Agent with Scalable Toolsets","created":"2025-10-24","cited_by_count":71},{"id":"2311.16714","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","created":"2023-11-28","cited_by_count":65},{"id":"2507.22844","title":"RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents","created":"2025-07-30","cited_by_count":58},{"id":"2501.11858","title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","created":"2025-01-21","cited_by_count":57},{"id":"2410.07706","title":"AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories","created":"2024-10-10","cited_by_count":56},{"id":"2406.14596","title":"VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought","created":"2024-06-20","cited_by_count":55},{"id":"2402.08178","title":"LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents","created":"2024-02-13","cited_by_count":51},{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50},{"id":"2310.08582","title":"Tree-Planner: Efficient Close-loop Task Planning with Large Language Models","created":"2023-10-12","cited_by_count":48},{"id":"2509.09265","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","created":"2025-09-11","cited_by_count":46},{"id":"2503.21696","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","created":"2025-03-27","cited_by_count":44},{"id":"2412.08442","title":"From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons","created":"2024-12-11","cited_by_count":42},{"id":"2503.02682","title":"MPO: Boosting LLM Agents with Meta Plan Optimization","created":"2025-03-04","cited_by_count":36},{"id":"2406.07904","title":"Grounding Multimodal Large Language Models in Actions","created":"2024-06-12","cited_by_count":35},{"id":"2308.07241","title":"Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents","created":"2023-08-14","cited_by_count":33},{"id":"2410.06237","title":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","created":"2024-10-08","cited_by_count":32},{"id":"2211.09935","title":"CAPE: Corrective Actions from Precondition Errors using Large Language Models","created":"2022-11-17","cited_by_count":30},{"id":"2409.09345","title":"Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models","created":"2024-09-14","cited_by_count":28},{"id":"2503.10480","title":"World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning","created":"2025-03-13","cited_by_count":26},{"id":"2510.17801","title":"Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain","created":"2025-10-20","cited_by_count":25},{"id":"2410.23968","title":"EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planning","created":"2024-10-31","cited_by_count":24},{"id":"2509.01106","title":"Robix: A Unified Model for Robot Interaction, Reasoning and Planning","created":"2025-09-01","cited_by_count":23},{"id":"2510.11027","title":"Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning","created":"2025-10-13","cited_by_count":23},{"id":"2502.12130","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","created":"2025-02-17","cited_by_count":19},{"id":"2505.03792","title":"Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning","created":"2025-05-01","cited_by_count":18},{"id":"2506.09049","title":"VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning","created":"2025-06-10","cited_by_count":18},{"id":"2503.06514","title":"GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks","created":"2025-03-09","cited_by_count":15},{"id":"2506.15677","title":"Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence","created":"2025-06-18","cited_by_count":15},{"id":"2506.21669","title":"SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents","created":"2025-06-26","cited_by_count":15},{"id":"2503.08525","title":"GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training","created":"2025-03-11","cited_by_count":14},{"id":"2505.22050","title":"Reinforced Reasoning for Embodied Planning","created":"2025-05-28","cited_by_count":12},{"id":"2407.19094","title":"Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs","created":"2024-07-26","cited_by_count":11},{"id":"2508.00344","title":"PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning","created":"2025-08-01","cited_by_count":11},{"id":"2508.03232","title":"CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios","created":"2025-08-05","cited_by_count":11},{"id":"2508.19076","title":"HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidance","created":"2025-08-26","cited_by_count":10},{"id":"2510.12693","title":"ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning","created":"2025-10-14","cited_by_count":10},{"id":"2506.21230","title":"World-aware Planning Narratives Enhance Large Vision-Language Model Planner","created":"2025-06-26","cited_by_count":9},{"id":"2506.23127","title":"Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning","created":"2025-06-29","cited_by_count":9},{"id":"2509.15273","title":"Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI","created":"2025-09-18","cited_by_count":9},{"id":"2406.11818","title":"Embodied Instruction Following in Unknown Environments","created":"2024-06-17","cited_by_count":8},{"id":"2503.15108","title":"VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making","created":"2025-03-19","cited_by_count":8},{"id":"2510.08759","title":"Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis","created":"2025-10-09","cited_by_count":8},{"id":"2510.09577","title":"Dyna-Mind: Learning to Simulate from Experience for Better AI Agents","created":"2025-10-10","cited_by_count":8},{"id":"2404.02255","title":"$\\texttt{LM}^\\texttt{2}$: A Simple Society of Language Models Solves Complex Reasoning","created":"2024-04-02","cited_by_count":7},{"id":"2404.15190","title":"Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following","created":"2024-04-21","cited_by_count":7},{"id":"2502.20742","title":"Structured Preference Optimization for Vision-Language Long-Horizon Task Planning","created":"2025-02-28","cited_by_count":7},{"id":"2506.06376","title":"Enhancing Decision-Making of Large Language Models via Actor-Critic","created":"2025-06-04","cited_by_count":7},{"id":"2508.11918","title":"ExploreVLM: Closed-Loop Robot Exploration Task Planning with Vision-Language Models","created":"2025-08-16","cited_by_count":7}],"next_cursor":"100"}