{"total":66,"rows":[{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611,"area":"lr"},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2411.16537","title":"RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics","created":"2024-11-25","cited_by_count":136,"area":"mllm"},{"id":"2506.09965","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","created":"2025-06-11","cited_by_count":136,"area":"lr"},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2404.03622","title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","created":"2024-04-04","cited_by_count":66,"area":"lr"},{"id":"2511.21471","title":"SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition","created":"2025-11-26","cited_by_count":35,"area":"mllm"},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2406.13948","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2409.20365","title":"VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs","created":"2024-09-30","cited_by_count":29,"area":"lr"},{"id":"2502.03214","title":"iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs","created":"2025-02-05","cited_by_count":25,"area":"lr"},{"id":"2505.17136","title":"Foundation Models for Geospatial Reasoning: Assessing Capabilities of Large Language Models in Understanding Geometries and Topological Spatial Relations","created":"2025-05-22","cited_by_count":23,"area":"lr"},{"id":"2406.14562","title":"Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2511.07403","title":"SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards","created":"2025-11-10","cited_by_count":16,"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":"2404.03429","title":"Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2408.14438","title":"Evaluating Large Language Models on Spatial Tasks: A Multi-Task Benchmarking Study","created":"2024-08-26","cited_by_count":12,"area":null},{"id":"2504.09848","title":"A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science","created":"2025-04-14","cited_by_count":12,"area":"wm"},{"id":"2406.19065","title":"STBench: Assessing the Ability of Large Language Models in Spatio-Temporal Analysis","created":"2024-06-27","cited_by_count":11,"area":null},{"id":"2406.16528","title":"Evaluating the Ability of Large Language Models to Reason about Cardinal Directions","created":"2024-06-24","cited_by_count":10,"area":"lr"},{"id":"2502.16690","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","created":"2025-02-23","cited_by_count":10,"area":"agents"},{"id":"2602.04850","title":"El Agente Quntur: A research collaborator agent for quantum chemistry","created":"2026-02-04","cited_by_count":8,"area":"agents"},{"id":"2406.15275","title":"How language models extrapolate outside the training data: A case study in Textualized Gridworld","created":"2024-06-21","cited_by_count":7,"area":null},{"id":"2407.01892","title":"GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning","created":"2024-07-02","cited_by_count":7,"area":"lr"},{"id":"2407.17404","title":"Grammar-based Game Description Generation using Large Language Models","created":"2024-07-24","cited_by_count":7,"area":null},{"id":"2503.09617","title":"Factorio Learning Environment","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2505.13484","title":"Evaluating Large Language Models for Real-World Engineering Tasks","created":"2025-05-12","cited_by_count":7,"area":null},{"id":"2411.07664","title":"Evaluating the Generation of Spatial Relations in Text and Image Generative Models","created":"2024-11-12","cited_by_count":6,"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":"2411.19589","title":"Can Large Language Models Reason about the Region Connection Calculus?","created":"2024-11-29","cited_by_count":5,"area":"lr"},{"id":"2505.17572","title":"USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2504.11571","title":"GraphicBench: A Planning Benchmark for Graphic Design with Language Agents","created":"2025-04-15","cited_by_count":4,"area":"agents"},{"id":"2504.14681","title":"An LLM-enabled Multi-Agent Autonomous Mechatronics Design Framework","created":"2025-04-20","cited_by_count":4,"area":"agents"},{"id":"2508.11286","title":"Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent","created":"2025-08-15","cited_by_count":4,"area":null},{"id":"2602.16105","title":"GPSBench: Do Large Language Models Understand GPS Coordinates?","created":"2026-02-18","cited_by_count":4,"area":"lr"},{"id":"2603.23864","title":"See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning","created":"2026-03-25","cited_by_count":4,"area":"lr"},{"id":"2604.00558","title":"STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPO","created":"2026-04-01","cited_by_count":4,"area":"lr"},{"id":"2607.08970","title":"MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2503.06218","title":"SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios","created":"2025-03-08","cited_by_count":3,"area":"lr"},{"id":"2512.19609","title":"MapTrace: Scalable Data Generation for Route Tracing on Maps","created":"2025-12-22","cited_by_count":3,"area":"mllm"},{"id":"2505.17482","title":"From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark","created":"2025-05-23","cited_by_count":2,"area":"lr"},{"id":"2506.08194","title":"GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra","created":"2025-06-09","cited_by_count":2,"area":"lr"},{"id":"2602.07082","title":"MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation","created":"2026-02-06","cited_by_count":2,"area":"lr"},{"id":"2506.00203","title":"The World As Large Language Models See It: Exploring the reliability of LLMs in representing geographical features","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.10853","title":"A Study on Individual Spatiotemporal Activity Generation Method Using MCP-Enhanced Chain-of-Thought Large Language Models","created":"2025-06-12","cited_by_count":1,"area":"lr"},{"id":"2507.12059","title":"Evaluating the Ability of Large Language Models to Reason about Cardinal Directions, Revisited","created":"2025-07-16","cited_by_count":1,"area":"lr"},{"id":"2510.14627","title":"GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2512.03558","title":"CartoMapQA: A Fundamental Benchmark Dataset Evaluating Vision-Language Models on Cartographic Map Understanding","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2601.21754","title":"Language-based Trial and Error Falls Behind in the Era of Experience","created":"2026-01-29","cited_by_count":1,"area":"agents"},{"id":"2603.26323","title":"From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs","created":"2026-03-27","cited_by_count":1,"area":"lr"},{"id":"2606.27378","title":"Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2608.14615","title":"Large Language Models and their Awareness of Mechanics and Spatial Geometry","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2409.06859","title":"NSP: A Neuro-Symbolic Natural Language Navigational Planner","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2502.00197","title":"Learning Model Successors","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2503.18769","title":"AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning","created":"2025-03-24","cited_by_count":0,"area":"lr"},{"id":"2504.02018","title":"Geometric Reasoning in the Embedding Space","created":"2025-04-02","cited_by_count":0,"area":"lr"},{"id":"2508.15222","title":"See it. Say it. Sorted: Agentic System for Compositional Diagram Generation","created":"2025-08-21","cited_by_count":0,"area":"agents"},{"id":"2512.06769","title":"Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding","created":"2025-12-07","cited_by_count":0,"area":"mllm"},{"id":"2601.14679","title":"HCVR Scene Generation: High Compatibility Virtual Reality Environment Generation for Extended Redirected Walking","created":"2026-01-21","cited_by_count":0,"area":null},{"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":"2604.14641","title":"Learning to Draw ASCII Improves Spatial Reasoning in Language Models","created":"2026-04-16","cited_by_count":0,"area":"lr"},{"id":"2605.06815","title":"Uneven Evolution of Cognition Across Generations of Generative AI Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.07066","title":"2.5-D Decomposition for LLM-Based Spatial Construction","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.30345","title":"SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2610.19443","title":"More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}