# MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks arXiv: https://arxiv.org/abs/2603.11554 ยท HTML: https://mlsanity.com/paper/2603.11554/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. - Builds on 42 of its 52 references that are in the map. - First posted on arXiv 12 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 42) - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022) - [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023) - [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024) - [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022) - [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023) - [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022) - [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017) - [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022) - [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022) - [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017) - [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017) - [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019) - [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023) - [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023) - [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021) - [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022) - [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021) - [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020) - [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022) - [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020) - [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022) - [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023) - [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023) - [TEACh: Task-driven Embodied Agents that Chat](https://mlsanity.com/paper/2110.00534/) (2021) - [BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation](https://mlsanity.com/paper/2403.09227/) (2024) - [Object-driven Text-to-Image Synthesis via Adversarial Training](https://mlsanity.com/paper/1902.10740/) (2019) - [AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes](https://mlsanity.com/paper/2312.06644/) (2023) - [HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising](https://mlsanity.com/paper/2211.13287/) (2022) - [ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation](https://mlsanity.com/paper/2409.13682/) (2024) - [GRUtopia: Dream General Robots in a City at Scale](https://mlsanity.com/paper/2407.10943/) (2024) ## Built on by (most cited first, 8 of 8) - [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026) - [FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute](https://mlsanity.com/paper/2609.08848/) (2026) - [PlanCraft: Sketch, Refine, and Furnish for Architect-Inspired Progressive 3D Residential Scene Generation](https://mlsanity.com/paper/2607.23491/) (2026) - [GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning](https://mlsanity.com/paper/2609.05927/) (2026) - [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026) - [To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation](https://mlsanity.com/paper/2608.05879/) (2026) - [ProxyBuild: Text-Guided Structured 3D Building Generation with Mesh-Anchored Procedural Proxies](https://mlsanity.com/paper/2609.23386/) (2026) - [Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation](https://mlsanity.com/paper/2609.32292/) (2026) ## Abstract (arXiv) Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks. We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments. Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes, enabling the development and evaluation of cross-floor long-horizon tasks. Building on this framework, we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices, alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs. Benchmarking reveals that state-of-the-art agents degrade sharply in our settings, establishing MANSION as a critical testbed for the next generation of spatial reasoning and planning.