{"total":71,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695,"area":"lr"},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706,"area":"lr"},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239,"area":"lr"},{"id":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177,"area":"lr"},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175,"area":"lr"},{"id":"2505.16421","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","created":"2025-05-22","cited_by_count":165,"area":"lr"},{"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,"area":"lr"},{"id":"2507.16746","title":"Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning","created":"2025-07-22","cited_by_count":84,"area":"lr"},{"id":"2307.00329","title":"DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment","created":"2023-07-01","cited_by_count":61,"area":"lr"},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60,"area":"lr"},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57,"area":"lr"},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"id":"2310.03249","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","created":"2023-10-05","cited_by_count":49,"area":"lr"},{"id":"2310.07018","title":"NEWTON: Are Large Language Models Capable of Physical Reasoning?","created":"2023-10-10","cited_by_count":45,"area":"lr"},{"id":"2503.21696","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","created":"2025-03-27","cited_by_count":44,"area":"lr"},{"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":"2410.05669","title":"ACPBench: Reasoning about Action, Change, and Planning","created":"2024-10-08","cited_by_count":39,"area":"lr"},{"id":"2310.03965","title":"Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models","created":"2023-10-06","cited_by_count":37,"area":"lr"},{"id":"2502.14276","title":"STeCa: Step-level Trajectory Calibration for LLM Agent Learning","created":"2025-02-20","cited_by_count":37,"area":"lr"},{"id":"2505.05622","title":"CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory","created":"2025-05-08","cited_by_count":32,"area":"lr"},{"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":"2407.07433","title":"Controllable Navigation Instruction Generation with Chain of Thought Prompting","created":"2024-07-10","cited_by_count":21,"area":"lr"},{"id":"2312.07062","title":"ThinkBot: Embodied Instruction Following with Thought Chain Reasoning","created":"2023-12-12","cited_by_count":19,"area":"lr"},{"id":"2502.12130","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","created":"2025-02-17","cited_by_count":19,"area":"lr"},{"id":"2304.00776","title":"Chain-of-Thought Predictive Control","created":"2023-04-03","cited_by_count":18,"area":"lr"},{"id":"2507.07644","title":"FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations","created":"2025-07-10","cited_by_count":13,"area":"lr"},{"id":"2505.22050","title":"Reinforced Reasoning for Embodied Planning","created":"2025-05-28","cited_by_count":12,"area":"lr"},{"id":"2506.17486","title":"Distilling On-device Language Models for Robot Planning with Minimal Human Intervention","created":"2025-06-20","cited_by_count":10,"area":"lr"},{"id":"2410.03907","title":"ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual Language Models in Household Activities","created":"2024-10-04","cited_by_count":9,"area":"lr"},{"id":"2503.16965","title":"Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning","created":"2025-03-21","cited_by_count":9,"area":"lr"},{"id":"2505.03035","title":"MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning","created":"2025-05-05","cited_by_count":9,"area":"lr"},{"id":"2506.21230","title":"World-aware Planning Narratives Enhance Large Vision-Language Model Planner","created":"2025-06-26","cited_by_count":9,"area":"lr"},{"id":"2603.11554","title":"MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks","created":"2026-03-12","cited_by_count":8,"area":"lr"},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2503.10042","title":"EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability","created":"2025-03-13","cited_by_count":6,"area":"lr"},{"id":"2505.18605","title":"Rethinking Causal Mask Attention for Vision-Language Inference","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"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":"2603.17312","title":"Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress","created":"2026-03-18","cited_by_count":6,"area":"lr"},{"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":"2407.07778","title":"WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment","created":"2024-07-10","cited_by_count":4,"area":"lr"},{"id":"2510.04141","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2211.01994","title":"lilGym: Natural Language Visual Reasoning with Reinforcement Learning","created":"2022-11-03","cited_by_count":3,"area":"lr"},{"id":"2505.16928","title":"Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2509.08500","title":"TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making","created":"2025-09-10","cited_by_count":3,"area":"lr"},{"id":"2512.23328","title":"CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations","created":"2025-12-29","cited_by_count":3,"area":"lr"},{"id":"2603.18859","title":"RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2605.12620","title":"Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2605.14504","title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2505.18028","title":"Knot So Simple: A Minimalistic Environment for Spatial Reasoning","created":"2025-05-23","cited_by_count":2,"area":"lr"},{"id":"2512.15940","title":"R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space","created":"2025-12-17","cited_by_count":2,"area":"lr"},{"id":"2601.10254","title":"NoReGeo: Non-Reasoning Geometry Benchmark","created":"2026-01-15","cited_by_count":2,"area":"lr"},{"id":"2603.10652","title":"Are Video Reasoning Models Ready to Go Outside?","created":"2026-03-11","cited_by_count":2,"area":"lr"},{"id":"2508.00356","title":"Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoning","created":"2025-08-01","cited_by_count":1,"area":"lr"},{"id":"2510.14828","title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2512.15933","title":"City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs","created":"2025-12-17","cited_by_count":1,"area":"lr"},{"id":"2407.09287","title":"Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments","created":"2024-07-12","cited_by_count":0,"area":"lr"},{"id":"2509.00465","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2512.15776","title":"Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active Querying","created":"2025-12-13","cited_by_count":0,"area":"lr"},{"id":"2603.17333","title":"Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.18495","title":"Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2604.19839","title":"Environmental Understanding Vision-Language Model for Embodied Agent","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2605.09860","title":"When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.11534","title":"PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.07962","title":"ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?","created":"2026-06-06","cited_by_count":0,"area":"lr"},{"id":"2607.22014","title":"Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents","created":"2026-07-24","cited_by_count":0,"area":"lr"},{"id":"2607.23055","title":"SymStep: Symbolic Step Verification for Logical Reasoning","created":"2026-07-25","cited_by_count":0,"area":"lr"},{"id":"2608.07905","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2610.17726","title":"TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}