# Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation

arXiv: https://arxiv.org/abs/2607.13653 · HTML: https://mlsanity.com/paper/2607.13653/

## Key facts

- Cited by 2 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 21 of its 59 references that are in the map.
- First posted on arXiv 15 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, 21 of 21)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [GRUtopia: Dream General Robots in a City at Scale](https://mlsanity.com/paper/2407.10943/) (2024)
- [RePLan: Robotic Replanning with Perception and Language Models](https://mlsanity.com/paper/2401.04157/) (2024)
- [RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration](https://mlsanity.com/paper/2505.03673/) (2025)
- [Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills](https://mlsanity.com/paper/2503.12533/) (2025)
- [ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning](https://mlsanity.com/paper/2510.12693/) (2025)
- [Simulating User Agents for Embodied Conversational-AI](https://mlsanity.com/paper/2410.23535/) (2024)
- [VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs](https://mlsanity.com/paper/2512.22342/) (2025)
- [ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making](https://mlsanity.com/paper/2505.20726/) (2025)
- [Communication-Efficient Desire Alignment for Embodied Agent-Human Adaptation](https://mlsanity.com/paper/2505.22503/) (2025)
- [EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making](https://mlsanity.com/paper/2510.12072/) (2025)
- [EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments](https://mlsanity.com/paper/2503.08604/) (2025)

## Built on by (most cited first, 2 of 2)

- [InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation](https://mlsanity.com/paper/2608.22990/) (2026)
- [DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents](https://mlsanity.com/paper/2609.40306/) (2026)

## Abstract (arXiv)

Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing frameworks often rely on privileged simulator states or assume complete instructions, bypassing realistic deployment challenges. To bridge this gap, we present REAL, an agentic framework for open-world mobile manipulation. REAL establishes sim-to-real-consistent environment APIs without oracle perception and integrates a simulated user to enable human-in-the-loop interaction. Within this environment, we design diverse task compositions to drive data collection, supervised fine-tuning, and online reinforcement learning, systematically optimizing agent performance. To comprehensively evaluate this approach, we introduce REAL-Bench, a benchmark spanning 241 tasks across active exploration, visual distraction, articulated manipulation, and interactive disambiguation. Experimental results demonstrate that our trained agent outperforms leading commercial closed-source VLMs on interactive tasks with a 56.9% success rate. Further empirical analysis reveals that our hierarchical training pipeline successfully aligns the model's tool-use capabilities while maintaining robust open-vocabulary reasoning under extended exploration horizons. Finally, we deploy and evaluate our framework on a physical dual-arm mobile robot, where it achieves a 78.3% end-to-end success rate over 60 real-world episodes. These physical trials demonstrate robust zero-shot transferability to unseen household scenarios, validating that our sim-to-real-consistent design successfully bridges the reality gap for long-horizon mobile manipulation. Code is available at https://github.com/InternRobotics/REAL.