# ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI arXiv: https://arxiv.org/abs/2607.04426 · HTML: https://mlsanity.com/paper/2607.04426/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. - Builds on 105 of its 169 references that are in the map. - First posted on arXiv 5 Jul 2026. ## Placed in - LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/) ## Builds on (most cited first, 30 of 105) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025) - [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023) - [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025) - [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024) - [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025) - [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025) - [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025) - [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025) - [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025) - [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023) - [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025) - [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024) - [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026) - [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019) - [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024) - [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026) - [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021) - [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024) - [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022) - [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025) - [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025) - [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026) - [GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation](https://mlsanity.com/paper/2410.06158/) (2024) - [MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?](https://mlsanity.com/paper/2408.13257/) (2024) - [Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout](https://mlsanity.com/paper/1904.04195/) (2019) - [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024) - [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020) - [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024) - [RT-H: Action Hierarchies Using Language](https://mlsanity.com/paper/2403.01823/) (2024) ## Built on by (most cited first, 5 of 5) - [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026) - [Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence](https://mlsanity.com/paper/2608.06756/) (2026) - [StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models](https://mlsanity.com/paper/2608.26067/) (2026) - [PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models](https://mlsanity.com/paper/2609.14973/) (2026) - [PF-RL: Progress Field Reinforcement Learning via Goal-Conditioned Value Geometry for Vision-Language-Action Models](https://mlsanity.com/paper/2609.32634/) (2026) ## Abstract (arXiv) Embodied AI is moving from isolated perception or action modules toward physical agents that understand, plan under goals, act through robot bodies, monitor progress, and improve from experience. Existing systems address this loop only in parts: end-to-end policies generate actions but often lack spatial reasoning, planning, and execution assessment, while robot-agent systems orchestrate tools or specialists but do not learn a shared representation. This fragmentation limits general Physical Agentic AI. We present ACE-Brain-0.5, a unified embodied foundation model that organizes robot intelligence into five coupled functions: spatial perception, decision making, embodied interaction, self-monitoring, and self-improvement. Built on ACE-Brain-0, which established spatial intelligence as a shared scaffold across robot platforms, ACE-Brain-0.5 extends an understanding-centric model into a closed-loop foundation model. A single 8B backbone instantiates the first four functions: grounding objects and affordances, reasoning over 3D and egocentric spatial relations, decomposing instructions into subgoals, generating navigation and manipulation actions, and estimating progress for verification and recovery. To unify these capabilities without cross-task interference, we introduce SSR+, which extends Scaffold-Specialize-Reconcile with a Reactivate stage after task-vector merging. The fifth function, self-improvement, is realized by a companion framework that updates external execution state, including task schemas, spatial memory, and failure-recovery cases, from rollouts. Across fifteen benchmarks, ACE-Brain-0.5 improves over ACE-Brain-0 on 14 of 18 spatial perception and grounding benchmarks, achieves competitive navigation and manipulation performance, and provides strong progress estimation in ID and OOD settings. Together, these results mark an early step toward general Physical Agentic AI.