# Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning

arXiv: https://arxiv.org/abs/2511.19516 · HTML: https://mlsanity.com/paper/2511.19516/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models](https://mlsanity.com/paper/2109.11797/) (2021)
- [GSVA: Generalized Segmentation via Multimodal Large Language Models](https://mlsanity.com/paper/2312.10103/) (2023)
- [UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling](https://mlsanity.com/paper/2111.12085/) (2021)
- [Learning to Compose and Reason with Language Tree Structures for Visual Grounding](https://mlsanity.com/paper/1906.01784/) (2019)
- [An Open and Comprehensive Pipeline for Unified Object Grounding and Detection](https://mlsanity.com/paper/2401.02361/) (2024)
- [Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models](https://mlsanity.com/paper/2308.13437/) (2023)
- [Learning Visual Grounding from Generative Vision and Language Model](https://mlsanity.com/paper/2407.14563/) (2024)
- [Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions](https://mlsanity.com/paper/2311.17048/) (2023)
- [GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection](https://mlsanity.com/paper/2312.15043/) (2023)
- [VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders](https://mlsanity.com/paper/2309.01141/) (2023)
- [When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network](https://mlsanity.com/paper/2506.17457/) (2025)

## Built on by (most cited first, 1 of 1)

- [Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning](https://mlsanity.com/paper/2605.31174/) (2026)

## Abstract (arXiv)

Visual grounding, the task of linking textual queries to specific regions within images, plays a pivotal role in vision-language integration. Existing methods typically rely on extensive task-specific annotations and fine-tuning, limiting their ability to generalize effectively to novel or out-of-distribution scenarios. To address these limitations, we introduce GroundingAgent, a novel agentic visual grounding framework that operates without any task-specific fine-tuning. GroundingAgent employs a structured, iterative reasoning mechanism that integrates pretrained open-vocabulary object detectors, multimodal large language models (MLLMs), and large language models (LLMs) to progressively refine candidate regions through joint semantic and spatial analyses. Remarkably, GroundingAgent achieves an average zero-shot grounding accuracy of 65.1 % on widely-used benchmarks (RefCOCO, RefCOCO+, RefCOCOg), entirely without fine-tuning. Furthermore, by substituting MLLM-generated captions with the original query texts, the accuracy at the selection stage alone reaches approximately 90 %, closely matching supervised performance and underscoring the critical role of LLM reasoning capabilities. GroundingAgent also offers strong interpretability, transparently illustrating each reasoning step and providing clear insights into its decision-making process.