# BRUCE: Benchmarking Robustness Under Corruption Escalation for Scientific Vision-Language Reasoning

arXiv: https://arxiv.org/abs/2608.07742 · HTML: https://mlsanity.com/paper/2608.07742/

## 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 19 of its 36 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## 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/)

## Builds on (most cited first, 19 of 19)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Do CIFAR-10 Classifiers Generalize to CIFAR-10?](https://mlsanity.com/paper/1806.00451/) (2018)
- [R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?](https://mlsanity.com/paper/2410.05474/) (2024)
- [Assessing the Chemical Intelligence of Large Language Models](https://mlsanity.com/paper/2505.07735/) (2025)
- [Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables](https://mlsanity.com/paper/2506.11375/) (2025)
- [MVTamperBench: Evaluating Robustness of Vision-Language Models](https://mlsanity.com/paper/2412.19794/) (2024)
- [Diagnosing Corruption-Induced Reliability Failures in Vision-Language Models](https://mlsanity.com/paper/2511.19032/) (2025)
- [mmJEE-Eval: A Bilingual Multimodal Benchmark for Evaluating Scientific Reasoning in Vision-Language Models](https://mlsanity.com/paper/2511.09339/) (2025)
- [Robust Reasoning Benchmark](https://mlsanity.com/paper/2604.08571/) (2026)
- [A Causally Grounded Taxonomy for Image Degradation Robustness Evaluation](https://mlsanity.com/paper/2605.15906/) (2026)

## Abstract (arXiv)

Visual-language models (VLMs) frequently struggle with robustness issues in real-world situations due to low- or varying-quality input images. In this paper, we aim at analyzing VLMs' robustness by applying perturbations and distortions to the input images, such as blur or low contrast. Toward this goal, we propose BRUCE (Benchmarking Robustness Under Corruption Escalation), a multimodal reasoning fragility framework for scientific vision-language reasoning. State-of-the-art evaluation frameworks/studies primarily focus on clean-task accuracy and rarely analyze how reasoning stability degrades across robustness dimensions. Besides varying over a wide-range of input perturbations, BRUCE employs two novel metrics -- Robustness Corruption Index (RCI) and Traversal-RCI (T-RCI) -- to quantify how rapidly multimodal reasoning performance deteriorates in VLMs as visual corruption severity increases under progressive perturbation scaling. We evaluate BRUCE across chemistry and mathematical reasoning tasks for multiple datasets, while analyzing corruption-induced prediction failures in terms of four high-level reasoning domains: OCR-dependent reasoning, spatial reasoning, symbolic reasoning, and semantic failures, with each containing fine-grained corruption specific failure subtypes, thereby enabling an interpretable failure analysis.