paper-with-me

Papers

FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis

2025-11-09 · Jan Ondras, Marek Šuppa arxiv

Mathematical reasoning requires abstracting symbolic rules from visual patterns -- inferring the infinite from the finite. We investigate whether multimodal AI systems possess this capability through FractalBench, a benchmark evaluating fractal program synthesis from images. Fractals provide ideal test cases: Iterated Function Systems with only a few contraction maps generate complex self-similar patterns through simple recursive rules, requiring models to bridge visual perception with mathematical abstraction. We evaluate four leading MLLMs -- GPT-4o, Claude 3.7 Sonnet, Gemini 2.5 Flash, and Qwen 2.5-VL -- on 12 canonical fractals. Models must generate executable Python code reproducing the fractal, enabling objective evaluation. Results reveal a striking disconnect: 76% generate syntactically valid code but only 4% capture mathematical structure. Success varies systematically -- models handle geometric transformations (Koch curves: 17-21%) but fail at branching recursion (trees: <2%), revealing fundamental gaps in mathematical abstraction. FractalBench provides a contamination-resistant diagnostic for visual-mathematical reasoning and is available at https://github.com/NaiveNeuron/FractalBench

📄 PDF Abstract BibTeX arXiv:2511.06522

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical ReasoningProgram Synthesis

Similar Papers 제목 키워드 기반

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

2026-05-19 · Xiaoou Liu, Tiejin Chen, Dengjia Zhang, Yaqing Wang 외 arxiv

Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning trace might fail remains difficult. Confi…

Multi-hop Question AnsweringMathematical Reasoning

Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphs

2026-05-26 · Jiaqiao Zhang, Zhoujun Li, Raoyuan Zhao, Jian Lan 외 arxiv

Large reasoning models (LRMs) achieve strong mathematical reasoning performance in English, but remain much less reliable in many low- and medium-resource languages. This gap is often explained as a failure to understand…

Mathematical Reasoning

Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training

2024-04-22 · Mengzhao Jia, Zhihan Zhang, Wenhao Yu, Fangkai Jiao 외

Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GP…

MathMathematical Reasoning

MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts

2025-02-28 · CVPR 2025 1 · Peijie Wang, Zhong-Zhi Li, Fei Yin, Xin Yang 외

Multimodal Large Language Models (MLLMs) have shown promising capabilities in mathematical reasoning within visual contexts across various datasets. However, most existing multimodal math benchmarks are limited to single…

MathMathematical ReasoningMultiple-choice

CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving

2026-01-05 · Shuhang Chen, Yunqiu Xu, Junjie Xie, Aojun Lu 외 arxiv

Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reas…

Information ExtractionMathematical Reasoning