{"total":139,"rows":[{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571,"area":"alignment"},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"area":null},{"id":"2305.16653","title":"AdaPlanner: Adaptive Planning from Feedback with Language Models","created":"2023-05-26","cited_by_count":196,"area":"agents"},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190,"area":"lr"},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175,"area":null},{"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,"area":null},{"id":"2406.04520","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","created":"2024-06-06","cited_by_count":128,"area":null},{"id":"2306.06531","title":"AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers","created":"2023-06-10","cited_by_count":113,"area":null},{"id":"2411.04549","title":"Vision Language Models are In-Context Value Learners","created":"2024-11-07","cited_by_count":90,"area":"mllm"},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2308.13724","title":"ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning","created":"2023-08-26","cited_by_count":77,"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":"2503.22674","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","created":"2025-03-28","cited_by_count":63,"area":"lr"},{"id":"2509.22195","title":"Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting","created":"2025-09-26","cited_by_count":58,"area":"lr"},{"id":"2405.14314","title":"Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration","created":"2024-05-23","cited_by_count":45,"area":"lr"},{"id":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","cited_by_count":43,"area":null},{"id":"2310.13065","title":"Creative Robot Tool Use with Large Language Models","created":"2023-10-19","cited_by_count":43,"area":"agents"},{"id":"2410.09918","title":"Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces","created":"2024-10-13","cited_by_count":43,"area":"lr"},{"id":"2306.17840","title":"Statler: State-Maintaining Language Models for Embodied Reasoning","created":"2023-06-30","cited_by_count":40,"area":"wm"},{"id":"2410.08792","title":"VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model","created":"2024-10-11","cited_by_count":37,"area":"mllm"},{"id":"2312.08566","title":"Learning adaptive planning representations with natural language guidance","created":"2023-12-13","cited_by_count":36,"area":null},{"id":"2406.07904","title":"Grounding Multimodal Large Language Models in Actions","created":"2024-06-12","cited_by_count":35,"area":"mllm"},{"id":"2404.03275","title":"DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2407.03321","title":"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages","created":"2024-07-03","cited_by_count":33,"area":null},{"id":"2409.20560","title":"LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner","created":"2024-09-30","cited_by_count":32,"area":"agents"},{"id":"2410.14660","title":"A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning","created":"2024-10-18","cited_by_count":30,"area":"alignment"},{"id":"2403.17246","title":"TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models","created":"2024-03-25","cited_by_count":29,"area":"agents"},{"id":"2407.21762","title":"ReplanVLM: Replanning Robotic Tasks with Visual Language Models","created":"2024-07-31","cited_by_count":28,"area":"mllm"},{"id":"2408.16090","title":"EPO: Hierarchical LLM Agents with Environment Preference Optimization","created":"2024-08-28","cited_by_count":28,"area":"agents"},{"id":"2406.19741","title":"ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning","created":"2024-06-28","cited_by_count":27,"area":"lr"},{"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":"2405.13245","title":"A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings","created":"2024-05-21","cited_by_count":24,"area":null},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2412.08542","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","created":"2024-12-11","cited_by_count":24,"area":null},{"id":"2306.14325","title":"The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs","created":"2023-06-25","cited_by_count":23,"area":null},{"id":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23,"area":null},{"id":"2410.12773","title":"Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions","created":"2024-10-16","cited_by_count":23,"area":null},{"id":"2409.02141","title":"Efficient and Scalable Estimation of Tool Representations in Vector Space","created":"2024-09-02","cited_by_count":22,"area":"agents"},{"id":"2410.16456","title":"To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning","created":"2024-10-21","cited_by_count":21,"area":null},{"id":"2404.02817","title":"A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches","created":"2024-04-03","cited_by_count":20,"area":null},{"id":"2502.17898","title":"VeriPlan: Integrating Formal Verification and LLMs into End-User Planning","created":"2025-02-25","cited_by_count":20,"area":null},{"id":"2503.18809","title":"Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code","created":"2025-03-24","cited_by_count":18,"area":null},{"id":"2407.12979","title":"Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models","created":"2024-07-17","cited_by_count":17,"area":null},{"id":"2504.21716","title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","created":"2025-04-30","cited_by_count":17,"area":"agents"},{"id":"2411.01775","title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","created":"2024-11-04","cited_by_count":16,"area":null},{"id":"2504.11844","title":"Evaluating the Goal-Directedness of Large Language Models","created":"2025-04-16","cited_by_count":16,"area":null},{"id":"2311.17406","title":"LLM-State: Open World State Representation for Long-horizon Task Planning with Large Language Model","created":"2023-11-29","cited_by_count":15,"area":null},{"id":"2505.21981","title":"Learning Compositional Behaviors from Demonstration and Language","created":"2025-05-28","cited_by_count":15,"area":"offlinerl"},{"id":"2509.13351","title":"Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning","created":"2025-09-14","cited_by_count":15,"area":"lr"},{"id":"2602.03036","title":"LatentMem: Customizing Latent Memory for Multi-Agent Systems","created":"2026-02-03","cited_by_count":15,"area":"agents"},{"id":"2406.17659","title":"DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning","created":"2024-06-25","cited_by_count":14,"area":"mllm"},{"id":"2402.16181","title":"How Can LLM Guide RL? A Value-Based Approach","created":"2024-02-25","cited_by_count":13,"area":null},{"id":"2505.22050","title":"Reinforced Reasoning for Embodied Planning","created":"2025-05-28","cited_by_count":12,"area":"lr"},{"id":"2402.16354","title":"Language-guided Skill Learning with Temporal Variational Inference","created":"2024-02-26","cited_by_count":11,"area":null},{"id":"2409.11276","title":"Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments","created":"2024-09-17","cited_by_count":9,"area":"agents"},{"id":"2410.05191","title":"LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic Manipulation","created":"2024-10-07","cited_by_count":9,"area":"mllm"},{"id":"2504.06553","title":"ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2405.01453","title":"Creative Problem Solving in Large Language and Vision Models -- What Would it Take?","created":"2024-05-02","cited_by_count":7,"area":null},{"id":"2406.12000","title":"Look Further Ahead: Testing the Limits of GPT-4 in Path Planning","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2407.21778","title":"Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Libraries","created":"2024-07-31","cited_by_count":7,"area":"agents"},{"id":"2504.13351","title":"Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2505.01009","title":"Improving Large Language Model Planning with Action Sequence Similarity","created":"2025-05-02","cited_by_count":7,"area":null},{"id":"2508.11918","title":"ExploreVLM: Closed-Loop Robot Exploration Task Planning with Vision-Language Models","created":"2025-08-16","cited_by_count":7,"area":"mllm"},{"id":"2508.18507","title":"Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies","created":"2025-08-25","cited_by_count":7,"area":"wm"},{"id":"2511.07568","title":"Procedural Knowledge Improves Agentic LLM Workflows","created":"2025-11-10","cited_by_count":7,"area":"agents"},{"id":"2511.09378","title":"Frontier Large Language Models Rival State-of-the-Art Planners","created":"2025-11-12","cited_by_count":7,"area":null},{"id":"2411.18711","title":"Evaluating Vision-Language Models as Evaluators in Path Planning","created":"2024-11-27","cited_by_count":6,"area":"lr"},{"id":"2506.16755","title":"Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-The-Fly","created":"2025-06-20","cited_by_count":6,"area":"lr"},{"id":"2506.19592","title":"Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning","created":"2025-06-24","cited_by_count":6,"area":"agents"},{"id":"2507.08496","title":"LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning","created":"2025-07-11","cited_by_count":6,"area":"lr"},{"id":"2410.24080","title":"Graph Learning for Numeric Planning","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2502.02066","title":"Anticipate & Act : Integrating LLMs and Classical Planning for Efficient Task Execution in Household Environments","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2512.09629","title":"End-to-end PDDL Planning with Hardcoded and Dynamic Agents","created":"2025-12-10","cited_by_count":5,"area":"agents"},{"id":"2310.14403","title":"O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2402.11489","title":"What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models","created":"2024-02-18","cited_by_count":4,"area":null},{"id":"2406.02598","title":"Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problems","created":"2024-06-01","cited_by_count":4,"area":null},{"id":"2410.01440","title":"Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2506.07062","title":"Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2510.24891","title":"Idea2Plan: Exploring AI-Powered Research Planning","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2505.14763","title":"Unifying Inference-Time Planning Language Generation","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2511.13765","title":"PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning","created":"2025-11-14","cited_by_count":3,"area":"alignment"},{"id":"2603.24018","title":"ELITE: Experiential Learning and Intent-Aware Transfer for Self-improving Embodied Agents","created":"2026-03-25","cited_by_count":3,"area":"mllm"},{"id":"2406.03757","title":"RoboCoder: Robotic Learning from Basic Skills to General Tasks with Large Language Models","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2409.18047","title":"HARMONIC: Cognitive and Control Collaboration in Human-Robotic Teams","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2410.13756","title":"CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2411.12829","title":"Human-Robot Dialogue Annotation for Multi-Modal Common Ground","created":"2024-11-19","cited_by_count":2,"area":null},{"id":"2412.00300","title":"Aligning LLM+PDDL Symbolic Plans with Human Objective Specifications through Evolutionary Algorithm Guidance","created":"2024-11-30","cited_by_count":2,"area":null},{"id":"2501.18816","title":"Large Language Models as Common-Sense Heuristics","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2502.20175","title":"An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs","created":"2025-02-27","cited_by_count":2,"area":"lr"},{"id":"2503.07317","title":"Self-Corrective Task Planning by Inverse Prompting with Large Language Models","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2503.08604","title":"EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2503.17339","title":"Can AI expose tax loopholes? Towards a new generation of legal policy assistants","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2505.12508","title":"InnateCoder: Learning Programmatic Options with Foundation Models","created":"2025-05-18","cited_by_count":2,"area":"deeprl"},{"id":"2506.11380","title":"Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation","created":"2025-06-13","cited_by_count":2,"area":null}],"next_cursor":"100"}