Pith. sign in

REVIEW 10 cited by

MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.00147 v1 pith:P3WUEFY3 submitted 2024-08-30 cs.CL cs.AI

Shuai Peng , Di Fu , Liangcai Gao , Xiuqin Zhong , Hongguang Fu , Zhi Tang This is my paper
classification cs.CLcs.AI
keywords mathematicalvisuallanguagelargemodelsmultimath-7bmultimodalreasoning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The rapid development of large language models (LLMs) has spurred extensive research into their domain-specific capabilities, particularly mathematical reasoning. However, most open-source LLMs focus solely on mathematical reasoning, neglecting the integration with visual injection, despite the fact that many mathematical tasks rely on visual inputs such as geometric diagrams, charts, and function plots. To fill this gap, we introduce \textbf{MultiMath-7B}, a multimodal large language model that bridges the gap between math and vision. \textbf{MultiMath-7B} is trained through a four-stage process, focusing on vision-language alignment, visual and math instruction-tuning, and process-supervised reinforcement learning. We also construct a novel, diverse and comprehensive multimodal mathematical dataset, \textbf{MultiMath-300K}, which spans K-12 levels with image captions and step-wise solutions. MultiMath-7B achieves state-of-the-art (SOTA) performance among open-source models on existing multimodal mathematical benchmarks and also excels on text-only mathematical benchmarks. Our model and dataset are available at {\textcolor{blue}{\url{https://github.com/pengshuai-rin/MultiMath}}}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MIRROR: Learning from the Other View for Multi-Modal Reasoning

    cs.AI 2026-07 conditional novelty 6.0 of 10

    An RL method that selects the best-performing view of each geometry problem as an internal teacher and distills it into weaker views improves VLM reasoning accuracy and consistency.

  2. TopoAgent: A Self-Evolving Topological Agent for Multimodal Scientific Reasoning

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A DAG-based agent framework using context isolation and runtime atomic fission reports average accuracy gains over linear agents on multimodal math, physics, and chemistry benchmarks.

  3. VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning

    cs.CV 2025-07 conditional novelty 6.0 of 10

    VL-Cogito, trained with progressive curriculum RL, online difficulty weighting, and dynamic length rewards, matches or beats prior reasoning MLLMs on ten multimodal benchmarks.

  4. Multimodal Mathematical Reasoning with Diverse Solving Perspective

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Training a multimodal language model on multiple diverse solution paths per problem, plus rewards for distinguishing correct from incorrect solutions, improves math benchmark accuracy and output diversity.

  5. VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection

    cs.CV 2025-05 conditional novelty 6.0 of 10

    VisTA uses GRPO reinforcement learning to train a vision-language agent to select external visual tools for a frozen reasoning model, improving accuracy on ChartQA, Geometry3K, BlindTest, and MathVerse.

  6. Evaluating Visual Mathematics in Multimodal LLMs: A Multilingual Benchmark Based on the Kangaroo Tests

    cs.AI 2025-06 conditional novelty 5.0 of 10

    A new multilingual, image-based Kangaroo math benchmark shows Gemini 2.0 Flash, Qwen-VL 2.5 72B, and GPT-4o lead current multimodal LLMs, but all remain far below human accuracy on visual math reasoning.

  7. MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

    cs.CV 2025-06 conditional novelty 5.0 of 10

    MINT-CoT-7B interleaves fine-grained visual tokens into each math reasoning step and reports 73.70 on MathVista-Math, 64.72 on GeoQA, and 69.6 on MMStar-Math.

  8. Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Using a two-stage SFT-plus-GRPO pipeline, the authors train 3B and 7B multimodal models that beat prior open-source models on four math reasoning benchmarks, while showing that reflective 'aha moment' text is not a re...

  9. GSM-Plus-BN: A Perturbation-Based Benchmark for Bangla Mathematical Reasoning in Large Language Models

    cs.CL 2026-07 conditional novelty 4.0 of 10

    The paper releases GSM-Plus-BN, a human-verified Bengali translation of the GSM-Plus perturbed math benchmark, and reports accuracy baselines for six open LLMs under standard and CoT prompting.

  10. A Survey of Deep Learning for Geometry Problem Solving

    cs.CL 2025-07 conditional novelty 4.0 of 10

    This survey organizes deep learning work on geometry problem solving into task, method, benchmark, and evaluation categories, and highlights open challenges.

Pith tools