# Thinking on Maps: How Foundation Model Agents Explore, Remember, and Reason Map Environments arXiv: https://arxiv.org/abs/2512.24504 ยท HTML: https://mlsanity.com/paper/2512.24504/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. - Builds on 26 of its 87 references that are in the map. - First posted on arXiv 30 Dec 2025. ## Placed in - LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/) ## Builds on (most cited first, 26 of 26) - [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022) - [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025) - [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023) - [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024) - [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023) - [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024) - [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025) - [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024) - [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025) - [Deep Learning the City : Quantifying Urban Perception At A Global Scale](https://mlsanity.com/paper/1608.01769/) (2016) - [RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent](https://mlsanity.com/paper/2406.07089/) (2024) - [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025) - [Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages](https://mlsanity.com/paper/2310.09340/) (2023) - [KnowGPT: Knowledge Graph based Prompting for Large Language Models](https://mlsanity.com/paper/2312.06185/) (2023) - [FlexiMo: A Flexible Remote Sensing Foundation Model](https://mlsanity.com/paper/2503.23844/) (2025) - [Foundation Models for Geospatial Reasoning: Assessing Capabilities of Large Language Models in Understanding Geometries and Topological Spatial Relations](https://mlsanity.com/paper/2505.17136/) (2025) - [NaviTrace: Evaluating Embodied Navigation of Vision-Language Models](https://mlsanity.com/paper/2510.26909/) (2025) - [Evaluating Large Language Models on Spatial Tasks: A Multi-Task Benchmarking Study](https://mlsanity.com/paper/2408.14438/) (2024) - [STBench: Assessing the Ability of Large Language Models in Spatio-Temporal Analysis](https://mlsanity.com/paper/2406.19065/) (2024) - [GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks](https://mlsanity.com/paper/2410.17031/) (2024) - [SeaMo: A Season-Aware Multimodal Foundation Model for Remote Sensing](https://mlsanity.com/paper/2412.19237/) (2024) - [GeoAnalystBench: A GeoAI benchmark for assessing large language models for spatial analysis workflow and code generation](https://mlsanity.com/paper/2509.05881/) (2025) - [Evaluation of Code LLMs on Geospatial Code Generation](https://mlsanity.com/paper/2410.04617/) (2024) - [MapColorAI: Designing Contextually Relevant Choropleth Map Color Schemes Using a Large Language Model](https://mlsanity.com/paper/2503.15502/) (2025) - [Learning Dynamic Cognitive Map with Autonomous Navigation](https://mlsanity.com/paper/2411.08447/) (2024) - [Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing](https://mlsanity.com/paper/2512.17224/) (2025) ## Built on by (most cited first, 1 of 1) - [Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation Model Spatial Understanding](https://mlsanity.com/paper/2607.17999/) (2026) ## Abstract (arXiv) Map environments provide a fundamental medium for representing spatial structure. Understanding how foundation model (FM) agents understand and act in such environments is therefore critical for enabling reliable map-based reasoning and applications. However, most existing evaluations of spatial ability in FMs rely on static map inputs or text-based queries, overlooking the interactive and experience-driven nature of spatial understanding.In this paper, we propose an interactive evaluation framework to analyze how FM agents explore, remember, and reason in symbolic map environments. Agents incrementally explore partially observable grid-based maps consisting of roads, intersections, and points of interest (POIs), receiving only local observations at each step. Spatial understanding is then evaluated using six kinds of spatial tasks. By systematically varying exploration strategies, memory representations, and reasoning schemes across multiple foundation models, we reveal distinct functional roles of these components. Exploration primarily affects experience acquisition but has a limited impact on final reasoning accuracy. In contrast, memory representation plays a central role in consolidating spatial experience, with structured memories particularly sequential and graph-based representations, substantially improving performance on structure-intensive tasks such as path planning. Reasoning schemes further shape how stored spatial knowledge is used, with advanced prompts supporting more effective multi-step inference. We further observe that spatial reasoning performance saturates across model versions and scales beyond a certain capability threshold, indicating that improvements in map-based spatial understanding require mechanisms tailored to spatial representation and reasoning rather than scaling alone.