# Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

arXiv: https://arxiv.org/abs/2512.17532 · HTML: https://mlsanity.com/paper/2512.17532/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 0 of its 35 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Built on by (most cited first, 7 of 7)

- [LongVideoAgent: Multi-Agent Reasoning with Long Videos](https://mlsanity.com/paper/2512.20618/) (2025)
- [TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration](https://mlsanity.com/paper/2603.27742/) (2026)
- [SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation](https://mlsanity.com/paper/2605.22536/) (2026)
- [Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?](https://mlsanity.com/paper/2606.08063/) (2026)
- [Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild](https://mlsanity.com/paper/2607.13881/) (2026)
- [VisualDeltas: Learning Preferences from Visual Quality Perturbations](https://mlsanity.com/paper/2603.07272/) (2026)
- [Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning](https://mlsanity.com/paper/2608.01314/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-the-art robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.