# MIRG-RL: Multi-Image Reasoning and Grounding with Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.21788 · HTML: https://mlsanity.com/paper/2509.21788/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 14 of 14)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models](https://mlsanity.com/paper/2408.04840/) (2024)
- [MANTIS: Interleaved Multi-Image Instruction Tuning](https://mlsanity.com/paper/2405.01483/) (2024)
- [Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring](https://mlsanity.com/paper/2403.09333/) (2024)
- [Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models](https://mlsanity.com/paper/2501.05767/) (2025)

## Built on by (most cited first, 3 of 3)

- [CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding](https://mlsanity.com/paper/2604.22498/) (2026)
- [Perceptual Flow Network for Visually Grounded Reasoning](https://mlsanity.com/paper/2605.02730/) (2026)
- [VAttnPO: Visual Attention-Guided Policy Optimization](https://mlsanity.com/paper/2610.16735/) (2026)

## Abstract (arXiv)

Multi-image reasoning and grounding require understanding complex cross-image relationships at both object levels and image levels. Current Large Visual Language Models (LVLMs) face two critical challenges: the lack of cross-image reasoning capabilities and insufficient cross-image reference reward modeling. To address these issues, we propose a unified framework - Multi-Image Reasoning and Grounding with Reinforcement Learning (MIRG-RL). Specifically, our two-stage training paradigm combines supervised fine-tuning with annotated trajectories and image-aware reinforcement learning optimization, progressively developing multi-image reasoning capabilities. Furthermore, we innovatively propose a method for constructing the trajectory data, which integrates object-level and image-level annotation information, and use this method to generate a lightweight reasoning-enhanced dataset. To effectively resolve cross-image ambiguities, we design an image-aware RL policy with dual reward functions for objects and images. Experiments demonstrate that MIRG-RL achieves state-of-the-art (SOTA) performance in multi-image grounding benchmarks, attaining 64.82% on cross-image reasoning tasks - exceeding the previous best method by 1%. The code and dataset have been released at https://github.com/ZEUS2035/MIRG-RL.