# SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments

arXiv: https://arxiv.org/abs/2604.22409 · HTML: https://mlsanity.com/paper/2604.22409/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 38 of its 46 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 38)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks](https://mlsanity.com/paper/2108.03272/) (2021)
- [RoboTHOR: An Open Simulation-to-Real Embodied AI Platform](https://mlsanity.com/paper/2004.06799/) (2020)
- [iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes](https://mlsanity.com/paper/2012.02924/) (2020)
- [ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models](https://mlsanity.com/paper/2505.21500/) (2025)
- [Visual Room Rearrangement](https://mlsanity.com/paper/2103.16544/) (2021)
- [MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation](https://mlsanity.com/paper/2012.03912/) (2020)
- [Multi-Target Embodied Question Answering](https://mlsanity.com/paper/1904.04686/) (2019)
- [Neural Modular Control for Embodied Question Answering](https://mlsanity.com/paper/1810.11181/) (2018)
- [Open3D-VQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space](https://mlsanity.com/paper/2503.11094/) (2025)
- [Egocentric Prediction of Action Target in 3D](https://mlsanity.com/paper/2203.13116/) (2022)
- [EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries](https://mlsanity.com/paper/2212.06969/) (2022)
- [SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence](https://mlsanity.com/paper/2505.17012/) (2025)
- [Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods](https://mlsanity.com/paper/2511.15722/) (2025)
- [ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks](https://mlsanity.com/paper/2412.13211/) (2024)
- [Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?](https://mlsanity.com/paper/2602.07055/) (2026)
- [Embodied Multimodal Multitask Learning](https://mlsanity.com/paper/1902.01385/) (2019)
- [MOPA: Modular Object Navigation with PointGoal Agents](https://mlsanity.com/paper/2304.03696/) (2023)
- [EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks](https://mlsanity.com/paper/2503.11089/) (2025)
- [A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search](https://mlsanity.com/paper/2206.13396/) (2022)
- [Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames](https://mlsanity.com/paper/2505.24257/) (2025)

## Built on by (most cited first, 6 of 6)

- [Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs](https://mlsanity.com/paper/2606.26387/) (2026)
- [4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding](https://mlsanity.com/paper/2605.05997/) (2026)
- [Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning](https://mlsanity.com/paper/2605.28277/) (2026)
- [EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks](https://mlsanity.com/paper/2609.28236/) (2026)
- [Long Time No See: Benchmarking VLMs for Out-of-Sight Spatiotemporal Reasoning in Egocentric Videos](https://mlsanity.com/paper/2609.34630/) (2026)
- [SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2610.12402/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where beliefs must be continuously revised from egocentric observations under environmental change. We introduce SpaMEM (Spatial Memory from Action Sequences), a large-scale diagnostic benchmark that isolates the mechanics of spatial belief evolution via action-conditioned scene transformations (spawn, place, remove) over long interaction horizons. SpaMEM is built on a physically grounded dataset with 10,601,392 high-fidelity images across four modalities (RGB, depth, instance, semantic segmentation), collected from 25,000+ interaction sequences in 1,000 procedurally generated houses. We formalize embodied spatial reasoning as a three-level hierarchy with 15 diagnostic tasks: Level 1 measures atomic spatial perception from single observations; Level 2 probes temporal reasoning with oracle textual state histories to factor out perceptual noise; and Level 3 requires end-to-end belief maintenance from raw visual streams under the same task dimensions. We further evaluate both short-term (step-wise) updates and long-term (episodic) reconstruction. Benchmarking representative open-source VLM families reveals a consistent stacked bottleneck: coordinate-consistent grounding remains a hard ceiling, and the sharp collapse from Level 2 to Level 3 exposes a pronounced symbolic scaffolding dependency, where models succeed with text-based bookkeeping but struggle to sustain robust visual memory. SpaMEM provides a granular diagnostic standard and motivates explicit mechanisms for state representation, belief revision, and long-horizon episodic integration. A subset of SpaMEM is publicly available at https://huggingface.co/datasets/mill-ct-liao/SpaMEM.