# From Passive Execution to Active Exploration: Agentic Embodied Manipulation in Realistic Environments

arXiv: https://arxiv.org/abs/2609.29091 · HTML: https://mlsanity.com/paper/2609.29091/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 8 references that are in the map.
- First posted on arXiv 24 Sep 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, 7 of 7)

- [Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation](https://mlsanity.com/paper/2403.08605/) (2024)
- [RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks](https://mlsanity.com/paper/2603.11558/) (2026)
- [Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied Agents](https://mlsanity.com/paper/2505.23450/) (2025)
- [Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation](https://mlsanity.com/paper/2307.06125/) (2023)
- [VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning](https://mlsanity.com/paper/2603.14523/) (2026)
- [SaiVLA-0: Cerebrum--Pons--Cerebellum Tripartite Architecture for Compute-Aware Vision-Language-Action](https://mlsanity.com/paper/2603.08124/) (2026)
- [RoboRetriever: Single-Camera Robot Object Retrieval via Active and Interactive Perception with Dynamic Scene Graph](https://mlsanity.com/paper/2508.12916/) (2025)

## Abstract (arXiv)

Recent advances in agentic systems have substantially enhanced the long-horizon capability of embodied manipulation. However, many existing frameworks still follow a passive execution paradigm, which limits their applicability to real-world scenarios involving textual semantic cues, distractors, and initially invisible targets. To bridge this gap, we propose an agent-based active exploration framework that enables robots to dynamically interact with the environment rather than merely execute predefined instructions. Specifically, our framework consists of three collaborative modules: a planning module for high-level task reasoning, a perception module for visual scene understanding, and an execution module for low-level manipulation. This design allows the robot to actively acquire task-relevant information, adapt its behavior based on environmental feedback, and complete manipulation tasks under partial observability. Furthermore, we introduce a fine-grained perception-execution interleaving strategy, which tightly couples visual feedback with skill execution to improve exploration robustness. We evaluate our method on a realistic Find-and-Place task, demonstrating its effectiveness in challenging environments where target objects must be actively discovered before manipulation.