# Finder: Agentic Closed-Loop Object Finding for Embodied Grounding

arXiv: https://arxiv.org/abs/2609.18058 · HTML: https://mlsanity.com/paper/2609.18058/

## 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 35 of its 50 references that are in the map.
- First posted on arXiv 16 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, 30 of 35)

- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [TEACh: Task-driven Embodied Agents that Chat](https://mlsanity.com/paper/2110.00534/) (2021)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization](https://mlsanity.com/paper/2201.13360/) (2022)
- [LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent](https://mlsanity.com/paper/2309.12311/) (2023)
- [Habitat-Matterport 3D Semantics Dataset](https://mlsanity.com/paper/2210.05633/) (2022)
- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [Clio: Real-time Task-Driven Open-Set 3D Scene Graphs](https://mlsanity.com/paper/2404.13696/) (2024)
- [Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships](https://mlsanity.com/paper/2402.12259/) (2024)
- [ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation](https://mlsanity.com/paper/2409.13682/) (2024)
- [Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces](https://mlsanity.com/paper/2503.19199/) (2025)
- [Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation](https://mlsanity.com/paper/2410.11989/) (2024)
- [Khronos: A Unified Approach for Spatio-Temporal Metric-Semantic SLAM in Dynamic Environments](https://mlsanity.com/paper/2402.13817/) (2024)
- [Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation](https://mlsanity.com/paper/2502.14254/) (2025)
- [EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planning](https://mlsanity.com/paper/2410.23968/) (2024)
- [Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interaction](https://mlsanity.com/paper/2508.05294/) (2025)
- [Describe Anything Anywhere At Any Moment](https://mlsanity.com/paper/2512.00565/) (2025)
- [Open-Vocabulary Online Semantic Mapping for SLAM](https://mlsanity.com/paper/2411.15043/) (2024)
- [FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graph](https://mlsanity.com/paper/2509.13733/) (2025)
- [OpenIN: Open-Vocabulary Instance-Oriented Navigation in Dynamic Domestic Environments](https://mlsanity.com/paper/2501.04279/) (2025)
- [Task-oriented Sequential Grounding and Navigation in 3D Scenes](https://mlsanity.com/paper/2408.04034/) (2024)
- [ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis](https://mlsanity.com/paper/2504.06553/) (2025)
- [DynamicGSG: Dynamic 3D Gaussian Scene Graphs for Environment Adaptation](https://mlsanity.com/paper/2502.15309/) (2025)
- [DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes](https://mlsanity.com/paper/2506.01950/) (2025)
- [Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration](https://mlsanity.com/paper/2512.02458/) (2025)

## Abstract (arXiv)

Finding the object referred to by language in a partially observed 3D scene is a core capability for embodied agents. Existing approaches either couple object search with online exploration, which can be costly when relevant observations have already been captured, or query pre-built open-vocabulary maps and scene graphs in a static, one-shot fashion. We present Finder, an agentic closed-loop object-finding primitive for embodied grounding. Instead of treating grounding as passive retrieval from a fixed scene representation, Finder maintains a typed loop state that links query-conditioned planning, scoped evidence gathering, candidate verification, and accept/continue/abort control. When evidence is incomplete or ambiguous, the loop can redirect subsequent perception and comparison rather than simply returning the top retrieved object. On open-vocabulary embodied Object Retrieval in Habitat/HM3D and real-world RGB-D scenes, Finder improves the averaged 1m success rate by 15.75 points over strong baselines. The same primitive also transfers to sequential object grounding and embodied object-centric question answering, improving spatial and temporal localization without changing the inner grounding protocol. Project page: https://finder-vln.github.io.