mlsanityData to 14 Oct 2026

MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph

arXiv 2610.12961 ↗First posted 9 Oct 2026cs.CV cs.CLcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

We introduce MVGraph, a benchmark for evaluating large vision-language models (LVLMs) on multi-graph reasoning where the evidence required by a query is distributed across multiple interrelated visual graph views. Although such evidence commonly resides in source-specific graphs, temporal snapshots, or local observations, existing graph reasoning benchmarks remain confined to a single self-contained structure, assessing only graph perception and reasoning while leaving the alignment and composition of evidence across views underexplored. MVGraph comprises 8k instances spanning 8 textitgraph-theoretic tasks, abstracted from two multi-graph scenarios (partial and temporal graph views). Each problem is programmatically constructed and verified to be unsolvable from a single view. Beyond end-to-end evaluation, we decompose multi-graph reasoning into four complementary capabilities---Perception, Alignment, Composition, and Reasoning---and design 29 diagnostic tasks with 64k instances to probe each one, along with golden intermediate representations for evaluating the intermediate process. Across 15 LVLMs, we reveal the difficulty of multi-graph reasoning and identify cross-view edge alignment and relation-level composition as prominent bottlenecks through stage-oriented diagnostics. Meanwhile, temporal constraints and increasing view counts expose further capability boundaries. Code and data are available at https://github.com/AAAndy-Zhu/MVGraph.

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 28 of its 38 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

28 of 38 references.

Closest ancestors · 11

Same direction, newest first

  1. 2026GraphVerse: A Comprehensive Visual Graph Reasoning Benchmark for Multimodal Large Language Models7 Aug
  2. 2026OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model22 Apr
  3. 2025Ovis2.5 Technical Report15 Aug
  4. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning1 Jul
  5. 2025Evaluating MLLMs with Multimodal Multi-image Reasoning Benchmark4 Jun
  6. 2025Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency24 Apr
  7. 2024Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning18 Dec
  8. 2024Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning18 Jun
  9. 2024ReMI: A Dataset for Reasoning with Multiple Images13 Jun
  10. 2024VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context8 May
  11. 2024GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning3 Feb

Other references · 17

  1. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  2. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  3. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 587
  4. 2019Representation Learning for Dynamic Graphs: A Surveycited by 265
  5. 2026Gemma 4 Technical Reportcited by 259
  6. 2023Can Language Models Solve Graph Problems in Natural Language?cited by 252
  7. 2024MuirBench: A Comprehensive Benchmark for Robust Multi-image Understandingcited by 188
  8. 2024MileBench: Benchmarking MLLMs in Long Contextcited by 88
  9. 2026DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compressioncited by 76
  10. 2024MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Modelscited by 67
  11. 2024MIBench: Evaluating Multimodal Large Language Models over Multiple Imagescited by 39
  12. 2024IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representationscited by 38
5 more
  1. 2024TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphscited by 36
  2. 2026On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stabilitycited by 35
  3. 2023Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Modelscited by 15
  4. 2024VisGraphVar: A Benchmark Generator for Assessing Variability in Graph Analysis Using Large Vision-Language Modelscited by 3
  5. 2025Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Modelscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models
  2. 2026HyperGVL: Benchmarking and Improving Large Vision-Language Models in Hypergraph Understanding and Reasoning
  3. 2026GraphVLM: Benchmarking Vision Language Models for Multimodal Graph Learning
  4. 2026Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models
  5. 2026Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models
  6. 2026Seeing Graphs Like Humans: Benchmarking Computational Measures and MLLMs for Similarity Assessment ↗
  7. 2026When Vision Meets Graphs: A Survey on Graph Reasoning and Learning
  8. 2025A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models