Data to 14 Oct 2026

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges

arXiv 2412.11936 ↗First posted 16 Dec 2024cs.CLcited by 55

On the map: LLM reasoning → Mathematical reasoning

also in 1 more

Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Mathematical reasoning, a core aspect of human cognition, is vital across many domains, from educational problem-solving to scientific advancements. As artificial general intelligence (AGI) progresses, integrating large language models (LLMs) with mathematical reasoning tasks is becoming increasingly significant. This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models (MLLMs). We review over 200 studies published since 2021, and examine the state-of-the-art developments in Math-LLMs, with a focus on multimodal settings. We categorize the field into three dimensions: benchmarks, methodologies, and challenges. In particular, we explore multimodal mathematical reasoning pipeline, as well as the role of (M)LLMs and the associated methodologies. Finally, we identify five major challenges hindering the realization of AGI in this domain, offering insights into the future direction for enhancing multimodal reasoning capabilities. This survey serves as a critical resource for the research community in advancing the capabilities of LLMs to tackle complex multimodal reasoning tasks.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 139 of its 210 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

139 of 210 references.

Closest ancestors · 43

Same direction, newest first

31 more

Other references · 96

2021Training Verifiers to Solve Math Word Problemscited by 10,109
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
2023BloombergGPT: A Large Language Model for Financecited by 939
2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928

38 more

2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 586
2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Datasetcited by 526
2022Visual Programming: Compositional visual reasoning without trainingcited by 516
2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 512
2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 487
2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 383
2024Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Modelscited by 268
2024DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Datacited by 234
2021GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoningcited by 228
2023G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Modelcited by 210
2022HyperTree Proof Search for Neural Theorem Provingcited by 197
2023OpenAGI: When LLM Meets Domain Expertscited by 197
2023Multimodal Large Language Models: A Surveycited by 195
2023TheoremQA: A Theorem-driven Question Answering datasetcited by 192
2024Large Language Models for Education: A Survey and Outlookcited by 188
2024MAmmoTH2: Scaling Instructions from the Webcited by 145
2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
2024Rho-1: Not All Tokens Are What You Needcited by 133
2023Large language models in healthcare and medical domain: A reviewcited by 127
2024Evaluation of OpenAI o1: Opportunities and Challenges of AGIcited by 127
2024M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thoughtcited by 121
2023SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Researchcited by 115
2024MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Enginecited by 113
2023GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoningcited by 108
2024MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmarkcited by 105
2023XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameterscited by 92
2023Quantifying & Modeling Multimodal Interactions: An Information Decomposition Frameworkcited by 83
2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
2023An In-Context Learning Agent for Formal Theorem-Provingcited by 82
2023UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Webcited by 78
2024A Survey of Multimodal Large Language Model from A Data-centric Perspectivecited by 75
2024Enhancing Large Vision Language Models with Self-Training on Image Comprehensioncited by 70
2023GPT Can Solve Mathematical Problems Without a Calculatorcited by 68
2024Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Datacited by 63
2023Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcarecited by 62
2023Collaborating with language models for embodied reasoningcited by 61

50 most cited of 96 All 96 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 38; 2026: 17.

55 papers.

Sort:

By area:

2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 199
2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
2025LLM Agents for Education: Advances and Applicationscited by 59
2025A Survey on Large Language Models for Mathematical Reasoningcited by 52
2025Reasoning Language Models: A Blueprintcited by 42
2025Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoningcited by 33
2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 33
2025SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearningcited by 32
2025MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Modelscited by 30
2025MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detectioncited by 24
2025Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?cited by 23

38 more

50 most cited of 55 All 55 (JSON)

Similar, not cited

Close in wording, no citation either way