# Thinking in 360deg: Humanoid Visual Search in the Wild

arXiv: https://arxiv.org/abs/2511.20351 · HTML: https://mlsanity.com/paper/2511.20351/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 73 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 30 of 50)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning](https://mlsanity.com/paper/2505.24298/) (2025)

## Built on by (most cited first, 15 of 15)

- [ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop](https://mlsanity.com/paper/2605.18746/) (2026)
- [VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments](https://mlsanity.com/paper/2512.15258/) (2025)
- [PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World](https://mlsanity.com/paper/2605.13169/) (2026)
- [See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning](https://mlsanity.com/paper/2603.23864/) (2026)
- [Towards Spatial Supersensing in the Wild](https://mlsanity.com/paper/2607.13681/) (2026)
- [E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes](https://mlsanity.com/paper/2604.17969/) (2026)
- [Planning with the Views](https://mlsanity.com/paper/2605.29563/) (2026)
- [Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models](https://mlsanity.com/paper/2606.02459/) (2026)
- [EAGOR: Embodied Reasoning in Omni-direction](https://mlsanity.com/paper/2607.06165/) (2026)
- [Panoramic Affordance Prediction](https://mlsanity.com/paper/2603.15558/) (2026)
- [Beyond Thinking: Imagining in 360^circ for Humanoid Visual Search](https://mlsanity.com/paper/2605.09146/) (2026)
- [WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence](https://mlsanity.com/paper/2607.06838/) (2026)
- [Enhancing In-context Panoramic Generation via Geometric-aware Pretraining](https://mlsanity.com/paper/2607.08765/) (2026)
- [Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans](https://mlsanity.com/paper/2608.16514/) (2026)
- [S-Space: Exploring Spatial Workspace in Multimodal Language Models](https://mlsanity.com/paper/2610.13527/) (2026)

## Abstract (arXiv)

Humans rely on the synergistic control of head (cephalomotor) and eye (oculomotor) to efficiently search for visual information in 360deg. However, prior approaches to visual search are limited to a static image, neglecting the physical embodiment and its interaction with the 3D world. How can we develop embodied visual search agents as efficient as humans while bypassing the constraints imposed by real-world hardware? To this end, we propose humanoid visual search where a humanoid agent actively rotates its head to search for objects or paths in an immersive world represented by a 360deg panoramic image. To study visual search in visually-crowded real-world scenarios, we build H* Bench, a new benchmark that moves beyond household scenes to challenging in-the-wild scenes that necessitate advanced visual-spatial reasoning capabilities, such as transportation hubs, large-scale retail spaces, urban streets, and public institutions. Our experiments first reveal that even top-tier proprietary models falter, achieving only ~30% success in object and path search. We then use post-training techniques to enhance the open-source Qwen2.5-VL, increasing its success rate by over threefold for both object search (14.83% to 47.38%) and path search (6.44% to 24.94%). Notably, the lower ceiling of path search reveals its inherent difficulty, which we attribute to the demand for sophisticated spatial commonsense. Our results not only show a promising path forward but also quantify the immense challenge that remains in building MLLM agents that can be seamlessly integrated into everyday human life.