# See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning

arXiv: https://arxiv.org/abs/2603.23864 · HTML: https://mlsanity.com/paper/2603.23864/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 47 of its 73 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 47)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training](https://mlsanity.com/paper/2509.23661/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (2025)
- [Imagine while Reasoning in Space: Multimodal Visualization-of-Thought](https://mlsanity.com/paper/2501.07542/) (2025)
- [MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence](https://mlsanity.com/paper/2505.23764/) (2025)
- [VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction](https://mlsanity.com/paper/2505.20279/) (2025)
- [Streaming 4D Visual Geometry Transformer](https://mlsanity.com/paper/2507.11539/) (2025)
- [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025)
- [StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding](https://mlsanity.com/paper/2411.03628/) (2024)
- [Cambrian-S: Towards Spatial Supersensing in Video](https://mlsanity.com/paper/2511.04670/) (2025)
- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [StreamingVLM: Real-Time Understanding for Infinite Video Streams](https://mlsanity.com/paper/2510.09608/) (2025)
- [RoboBrain 2.0 Technical Report](https://mlsanity.com/paper/2507.02029/) (2025)
- [Scaling Spatial Intelligence with Multimodal Foundation Models](https://mlsanity.com/paper/2511.13719/) (2025)
- [Evaluating Spatial Understanding of Large Language Models](https://mlsanity.com/paper/2310.14540/) (2023)
- [Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2510.12635/) (2025)
- [Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes](https://mlsanity.com/paper/2509.06266/) (2025)
- [GRUtopia: Dream General Robots in a City at Scale](https://mlsanity.com/paper/2407.10943/) (2024)
- [VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2410.13860/) (2024)

## Built on by (most cited first, 4 of 4)

- [SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding](https://mlsanity.com/paper/2606.22694/) (2026)
- [Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation](https://mlsanity.com/paper/2609.29934/) (2026)
- [From Reasoning Failures to Composable Video Spatial Intelligence](https://mlsanity.com/paper/2610.01999/) (2026)
- [DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding](https://mlsanity.com/paper/2610.19849/) (2026)

## Abstract (arXiv)

Spatial understanding is fundamental for embodied agents, yet most spatial VLMs and benchmarks remain offline-evaluating post-hoc QA over pre-recorded inputs and overlooking two crucial deployment-critical requirements: long-horizon streaming inference and active perception when the current view is insufficient. To address this gap, we introduce S3-Bench, a benchmark suite for streaming spatial question answering with active exploration, where queries are temporally grounded to specific timestamps and must be answered using only observations available up to that moment. S3-Bench adopts a dual-domain design, combining a scalable simulator with controllable trajectories and exploration actions, and real-world streaming videos that capture practical sensing artifacts for rigorous generalization evaluation. Overall, it spans 10K+ scenes and 26K+ trajectories, with dedicated training (S3-Train) and evaluation (S3-Eval) splits. We further propose AMF-VLM, which supports streaming spatial reasoning under bounded computing via (i) memory folding, which compresses long-horizon observations into compact structured memory, and (ii) active exploration, which outputs explicit actions (e.g. move/rotate/scan) to acquire missing evidence before answering. Extensive experiments demonstrate that, compared to models using identical training data, our approach yields improvements of 8.8% and 13.3% on the simulated and real splits of S3-Eval, respectively, while maintaining competitive transferability to standard spatial benchmarks.