# ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop

arXiv: https://arxiv.org/abs/2605.18746 · HTML: https://mlsanity.com/paper/2605.18746/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 17 of 17)

- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents](https://mlsanity.com/paper/2502.09560/) (2025)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (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)
- [SpatialBot: Precise Spatial Understanding with Vision Language Models](https://mlsanity.com/paper/2406.13642/) (2024)
- [3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark](https://mlsanity.com/paper/2412.07825/) (2024)
- [Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing](https://mlsanity.com/paper/2506.09965/) (2025)
- [SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning](https://mlsanity.com/paper/2501.10074/) (2025)
- [EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents](https://mlsanity.com/paper/2501.11858/) (2025)
- [Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering](https://mlsanity.com/paper/2503.11117/) (2025)
- [ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation](https://mlsanity.com/paper/2601.08325/) (2026)
- [Thinking in 360deg: Humanoid Visual Search in the Wild](https://mlsanity.com/paper/2511.20351/) (2025)
- [CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning](https://mlsanity.com/paper/2601.13304/) (2026)
- [From Perception to Action: An Interactive Benchmark for Vision Reasoning](https://mlsanity.com/paper/2602.21015/) (2026)
- [ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models](https://mlsanity.com/paper/2603.13033/) (2026)

## Built on by (most cited first, 26 of 26)

- [Self-Evolving Embodied Agents via Skill-Harness Evolution](https://mlsanity.com/paper/2608.11350/) (2026)
- [OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs](https://mlsanity.com/paper/2606.03890/) (2026)
- [SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity](https://mlsanity.com/paper/2606.25634/) (2026)
- [WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation](https://mlsanity.com/paper/2606.26443/) (2026)
- [SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion](https://mlsanity.com/paper/2606.27876/) (2026)
- [HumanCLAW: Can Vision-Language Models Act Through a Body?](https://mlsanity.com/paper/2607.27180/) (2026)
- [Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?](https://mlsanity.com/paper/2606.01247/) (2026)
- [PROBE: Manipulation-Grounded Visual Question Answering with VLM Agents](https://mlsanity.com/paper/2608.17129/) (2026)
- [RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction](https://mlsanity.com/paper/2608.28718/) (2026)
- [VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control](https://mlsanity.com/paper/2609.19554/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [ParallelWorld: Test-Time Scaling for Embodied Reasoning](https://mlsanity.com/paper/2608.22971/) (2026)
- [MindTopo: Can Foundation Models Reason in Topological Space?](https://mlsanity.com/paper/2609.11900/) (2026)
- [Space as an Interventional Invariant: Cross-Modal Predictive Geometry for Stratified Cities and Em-Spaced Intelligence](https://mlsanity.com/paper/2609.11959/) (2026)
- [ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation](https://mlsanity.com/paper/2609.24124/) (2026)
- [Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation](https://mlsanity.com/paper/2609.29934/) (2026)
- [SpatialSkill: Self-Evolving Skills for Cross-View Spatial Reasoning](https://mlsanity.com/paper/2609.34124/) (2026)
- [VCN-Bench: A Video-Contextualized Navigation Benchmark for Spatial Reasoning over Prior Visual Experience](https://mlsanity.com/paper/2609.34687/) (2026)
- [Who Is Left of Whom? Tracing Spatial Evidence and Role Binding in Relative-Position Reasoning](https://mlsanity.com/paper/2609.35486/) (2026)
- [ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perception](https://mlsanity.com/paper/2610.06955/) (2026)
- [Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild](https://mlsanity.com/paper/2610.11328/) (2026)
- [Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing](https://mlsanity.com/paper/2610.12881/) (2026)
- [S-Space: Exploring Spatial Workspace in Multimodal Language Models](https://mlsanity.com/paper/2610.13527/) (2026)
- [SpatialASM: Internalizing Active Mentalization for Spatial Reasoning](https://mlsanity.com/paper/2610.13832/) (2026)
- [MemAct: Streaming Spatial Understanding with Memory and Active Exploration](https://mlsanity.com/paper/2610.17640/) (2026)
- [Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence](https://mlsanity.com/paper/2610.20312/) (2026)

## Abstract (arXiv)

Spatial intelligence unfolds through a perception-action loop: agents act to acquire observations, and reason about how observations vary as a function of action. Rather than passively processing what is seen, they actively uncover what is unseen - occluded structure, dynamics, containment, and functionality that cannot be resolved from passive sensing alone. We move beyond prior formulations of spatial intelligence that assume oracle observations by recasting the observer as an actor. We introduce ESI-BENCH, a comprehensive benchmark for embodied spatial intelligence spanning 10 task categories and 29 subcategories built on OmniGibson, grounded in Spelke's core knowledge systems. Agents must decide what abilities to deploy - perception, locomotion, and manipulation - and how to sequence them to actively accumulate task-relevant evidence. We conduct extensive experiments on state-of-the-art MLLMs and find that active exploration substantially outperforms passive counterparts, with agents spontaneously discovering emergent spatial strategies without explicit instructions, while random multi-view often adds noise rather than signal despite consuming far more images. Most failures stem not from weak perception but from action blindness: poor action choices lead to poor observations, which in turn drive cascading errors. While explicit 3D grounding stabilizes reasoning on depth-sensitive tasks, imperfect 3D representation proves more harmful than 2D baselines by distorting spatial relations. Human studies further reveal that unlike humans who seek falsifying viewpoints and revise beliefs under contradiction, models commit prematurely with high confidence regardless of evidence quality, exposing a metacognitive gap that neither better perception nor more embodied interaction alone can close.