# Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding

arXiv: https://arxiv.org/abs/2509.25794 · HTML: https://mlsanity.com/paper/2509.25794/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 39 of its 58 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## 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 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics](https://mlsanity.com/paper/2406.10721/) (2024)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents](https://mlsanity.com/paper/2502.09560/) (2025)
- [Any-point Trajectory Modeling for Policy Learning](https://mlsanity.com/paper/2401.00025/) (2023)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)
- [Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning](https://mlsanity.com/paper/2503.15558/) (2025)
- [RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete](https://mlsanity.com/paper/2502.21257/) (2025)
- [RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches](https://mlsanity.com/paper/2311.01977/) (2023)
- [HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation](https://mlsanity.com/paper/2502.05485/) (2025)
- [RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2506.04308/) (2025)
- [EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models](https://mlsanity.com/paper/2406.05756/) (2024)
- [General Flow as Foundation Affordance for Scalable Robot Learning](https://mlsanity.com/paper/2401.11439/) (2024)
- [Manipulate-Anything: Automating Real-World Robots using Vision-Language Models](https://mlsanity.com/paper/2406.18915/) (2024)
- [Gemini Robotics: Bringing AI into the Physical World](https://mlsanity.com/paper/2503.20020/) (2025)
- [Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents](https://mlsanity.com/paper/2303.00855/) (2023)

## Built on by (most cited first, 10 of 10)

- [LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight](https://mlsanity.com/paper/2511.20648/) (2025)
- [Hy-Embodied-VLM-1.0: Efficient Physical-World Agents](https://mlsanity.com/paper/2607.12894/) (2026)
- [Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models](https://mlsanity.com/paper/2606.11324/) (2026)
- [Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRI](https://mlsanity.com/paper/2604.15808/) (2026)
- [NewtPhys: Do Foundation Models Understand Newtonian Physics?](https://mlsanity.com/paper/2606.03986/) (2026)
- [SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation](https://mlsanity.com/paper/2605.10376/) (2026)
- [Position: The Systemic Lack of Agency in Visual Reasoning](https://mlsanity.com/paper/2606.14795/) (2026)
- [RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation](https://mlsanity.com/paper/2607.18709/) (2026)
- [Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence](https://mlsanity.com/paper/2608.06756/) (2026)
- [PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models](https://mlsanity.com/paper/2609.14973/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) have demonstrated impressive world knowledge across a wide range of tasks, making them promising candidates for embodied reasoning applications. However, existing benchmarks primarily evaluate the embodied reasoning ability of VLMs through multiple-choice questions based on image annotations -- for example, selecting which trajectory better describes an event in the image. In this work, we introduce the Point-It-Out (PIO) benchmark, a novel benchmark designed to systematically assess the embodied reasoning abilities of VLMs through precise visual grounding. We propose a hierarchical evaluation protocol spanning three stages (S1: referred-object localization, S2: task-driven pointing, and S3: visual trace prediction), with data collected from critical domains for embodied intelligence, including indoor, kitchen, driving, and robotic manipulation scenarios. Extensive experiments with over ten state-of-the-art VLMs reveal several interesting findings. For example, strong general-purpose models such as GPT-4o, while excelling on many benchmarks (e.g., language, perception, and reasoning), underperform compared to some open-source models in precise visual grounding; models such as MoLMO perform well in S1 and S2 but struggle in S3, where requires grounding combined with visual trace planning.