Pith. sign in

REVIEW 4 cited by

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

Not yet reviewed by Pith; the record is open.

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 2502.20808 v6 pith:6NQIRHD3 submitted 2025-02-28 cs.AI

classification cs.AI
keywords mathematicalmulti-visualcontextsmllmsmv-mathreasoningcapabilitiesmath
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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-visual contexts, which diverges from the multi-visual scenarios commonly encountered in real-world mathematical applications. To address this gap, we introduce MV-MATH: a meticulously curated dataset of 2,009 high-quality mathematical problems. Each problem integrates multiple images interleaved with text, derived from authentic K-12 scenarios, and enriched with detailed annotations. MV-MATH includes multiple-choice, free-form, and multi-step questions, covering 11 subject areas across 3 difficulty levels, and serves as a comprehensive and rigorous benchmark for assessing MLLMs' mathematical reasoning in multi-visual contexts. Through extensive experimentation, we observe that MLLMs encounter substantial challenges in multi-visual math tasks, with a considerable performance gap relative to human capabilities on MV-MATH. Furthermore, we analyze the performance and error patterns of various models, providing insights into MLLMs' mathematical reasoning capabilities within multi-visual settings.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning

    cs.CV 2025-06 conditional novelty 6.0 of 10

    PeRL applies reinforcement learning to a vision-language model with image-order permutation and difficulty-based data filtering, improving multi-image reasoning while keeping single-image performance.

  2. MATP-BENCH: Can MLLM Be a Good Automated Theorem Prover for Multimodal Problems?

    cs.CL 2025-06 conditional novelty 6.0 of 10

    MATP-BENCH pairs 1,056 multimodal math problems with formal theorem statements in Lean 4, Coq, and Isabelle; the strongest tested model solves only 5.68% of Lean 4 end-to-end proving tasks at pass@10.

  3. Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models

    cs.CL 2025-05 conditional novelty 2.0 of 10

    A survey-style position paper claims that reinforcement fine-tuning powers reasoning in multimodal LLMs, summarizing over a hundred recent works and proposing five future research directions.

  4. Large Language Models as Computable Approximations to Solomonoff Induction

    cs.LG 2025-05 reject novelty 2.0 of 10

    The paper argues LLMs are computable approximations of Solomonoff induction, but its central derivation recovers the model's own probabilities by construction.

Pith tools