# RGBX-R1: Visual Modality Chain-of-Thought Guided Reinforcement Learning for Multimodal Grounding

arXiv: https://arxiv.org/abs/2602.00504 · HTML: https://mlsanity.com/paper/2602.00504/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 41 of its 45 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 41)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [Visual Prompt Multi-Modal Tracking](https://mlsanity.com/paper/2303.10826/) (2023)
- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [RGB-T Object Tracking:Benchmark and Baseline](https://mlsanity.com/paper/1805.08982/) (2018)
- [LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking](https://mlsanity.com/paper/2104.13202/) (2021)
- [UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning](https://mlsanity.com/paper/2505.14231/) (2025)
- [DepthTrack : Unveiling the Power of RGBD Tracking](https://mlsanity.com/paper/2108.13962/) (2021)
- [Single-Model and Any-Modality for Video Object Tracking](https://mlsanity.com/paper/2311.15851/) (2023)
- [OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning](https://mlsanity.com/paper/2403.09634/) (2024)
- [Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking](https://mlsanity.com/paper/2412.15691/) (2024)
- [SUTrack: Towards Simple and Unified Single Object Tracking](https://mlsanity.com/paper/2412.19138/) (2024)
- [Bi-directional Adapter for Multi-modal Tracking](https://mlsanity.com/paper/2312.10611/) (2023)

## Abstract (arXiv)

Multimodal Large Language Models (MLLM) are primarily pre-trained on the RGB modality, thereby limiting their performance on other modalities, such as infrared, depth, and event data, which are crucial for complex scenarios. To address this, we propose RGBX-R1, a framework to enhance MLLM's perception and reasoning capacities across various X visual modalities. Specifically, we employ an Understand-Associate-Validate (UAV) prompting strategy to construct the Visual Modality Chain-of-Thought (VM-CoT), which aims to expand the MLLMs' RGB understanding capability into X modalities. To progressively enhance reasoning capabilities, we introduce a two-stage training paradigm: Cold-Start Supervised Fine-Tuning (CS-SFT) and Spatio-Temporal Reinforcement Fine-Tuning (ST-RFT). CS-SFT supervises the reasoning process with the guidance of VM-CoT, equipping the MLLM with fundamental modality cognition. Building upon GRPO, ST-RFT employs a Modality-understanding Spatio-Temporal (MuST) reward to reinforce modality reasoning. Notably, we construct the first RGBX-Grounding benchmark, and extensive experiments verify our superiority in multimodal understanding and spatial perception, outperforming baselines by 22.71% on three RGBX grounding tasks.