In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs. We propose MIRROR, a framework for multimodal iterative reasoning via reflection on visual regions. By embedding visual reflection as a core mechanism, MIRROR follows a closed-loop process: draft, critique, region-based verification, and revision. To support this, we construct ReflectV, a dataset for multi-turn supervision. Experiments show MIRROR significantly improves correctness and reduces hallucinations.
MIRROR upgrades standard VLM inference into a cycle of drafting, critiquing, and region-based verification to anchor reasoning in concrete visual evidence.
ReflectV transforms static QA into 24k high-quality reflective trajectories using a multi-agent pipeline and self-reflective conversion.
Performance on General Capabilities and OCR & Document Benchmarks.
| Model | Size | MM-Vet | MMStar | Seed-2-P | TextVQA | OCRBench | ChartQA |
|---|---|---|---|---|---|---|---|
| LLaVA-OneVision | 7B | 48.80 | 61.70 | -- | 76.10 | 62.10 | 80.00 |
| InternVL3 | 2B | 54.95 | 60.70 | 64.95 | 77.00 | 82.20 | 76.08 |
| InternVL3 | 8B | 64.27 | 61.50 | 69.61 | 80.51 | 85.00 | 79.64 |
| Qwen2.5-VL-3B | 3B | 47.39 | 55.87 | 68.81 | 79.12 | 82.60 | 83.20 |
| Qwen2.5-VL-7B | 7B | 56.60 | 61.21 | 70.88 | 84.90 | 83.20 | 86.08 |
| MIRROR (w/o tool) | 7B | 59.91 | 62.80 | 70.36 | 85.37 | 88.30 | 86.56 |
| MIRROR (ours) | 7B | 66.70 | 73.33 | 76.86 | 86.62 | 92.00 | 87.92 |
Performance on Hallucination, Perception, and Math Benchmarks.
| Model | Size | POPE | HalluBench | HRBench-4k | MME-RW | VStarBench | MathVison |
|---|---|---|---|---|---|---|---|
| LLaVA-OneVision | 7B | 78.10 | 31.60 | 63.00 | -- | 72.30 | 18.30 |
| InternVL3 | 2B | 89.60 | 42.50 | 61.75 | 43.88 | 68.59 | 21.71 |
| InternVL3 | 8B | 90.37 | 49.90 | 70.00 | 48.83 | 68.06 | 20.39 |
| Qwen2.5-VL-3B | 3B | 86.21 | 63.09 | 50.25 | 42.15 | 72.77 | 25.66 |
| Qwen2.5-VL-7B | 7B | 86.45 | 68.66 | 68.87 | 44.29 | 75.39 | 23.36 |
| MIRROR (w/o tool) | 7B | 87.95 | 68.24 | 69.13 | 46.01 | 76.44 | 27.30 |
| MIRROR (ours) | 7B | 94.42 | 82.02 | 72.88 | 51.49 | 83.77 | 28.29 |
MIRROR addresses the inherent limitations of Text Reflection and Thinking with Images by incorporating a targeted feedback loop.
| Method | OCRBench | POPE | MME-RW | MMVet |
|---|---|---|---|---|
| Text Reflection | ||||
| VL-Rethinker | 85.40 | 84.19 | 47.21 | 56.19 |
| Thinking with Images | ||||
| PixelReasoner | 82.10 | 86.03 | 49.70 | 52.98 |
| DeepEyes | 88.10 | 87.70 | 49.50 | 60.28 |
| Adaptive-CoF | 86.00 | 89.30 | 50.90 | 66.21 |
| MIRROR (ours) | 92.00 | 94.42 | 51.49 | 66.70 |
MIRROR demonstrates superior Spatial Reasoning by identifying counting errors and Object Identification via active point-based querying.
MIRROR: Multimodal Iterative Reasoning via Reflection On Visual Regions
@article{zhang2026mirror,
title={MIRROR: Multimodal Iterative Reasoning via Reflection On Visual Regions},
author={Zhang, Haoyu and Wu, Yuwei and Li, Pengxiang and Zhang, Xintong and Gao, Zhi and Gao, Rui and Gao, Mingyang and Sun, Che and Jia, Yunde},
journal={arXiv preprint arXiv:2602.18746},
year={2026}
}