mlsanityData to 7 Oct 2026

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

arXiv 2603.02024 ↗First posted 2 Mar 2026cs.CL cs.AI cs.CVcited by 8

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Recent progress in the reasoning capabilities of multimodal large language models (MLLMs) has empowered them to address more complex tasks such as scientific analysis and mathematical reasoning. Despite their promise, MLLMs' reasoning abilities across different scenarios in real life remain largely unexplored and lack standardized benchmarks for evaluation. To address this gap, we introduce MMR-Life, a comprehensive benchmark designed to evaluate the diverse multimodal multi-image reasoning capabilities of MLLMs across real-life scenarios. MMR-Life consists of 2,646 multiple-choice questions based on 19,108 images primarily sourced from real-world contexts, comprehensively covering seven reasoning types: abductive, analogical, causal, deductive, inductive, spatial, and temporal. Unlike existing reasoning benchmarks, MMR-Life does not rely on domain-specific expertise but instead requires models to integrate information across multiple images and apply diverse reasoning abilities. The evaluation of 37 advanced models highlights the substantial challenge posed by MMR-Life. Even top models like GPT-5 achieve only 58% accuracy and display considerable variance in performance across reasoning types. Moreover, we analyze the reasoning paradigms of existing MLLMs, exploring how factors such as thinking length, reasoning method, and reasoning type affect their performance. In summary, MMR-Life establishes a comprehensive foundation for evaluating, analyzing, and improving the next generation of multimodal reasoning systems.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 35 of its 76 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

35 of 76 references.

Closest ancestors · 20

Same direction, newest first

  1. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency25 Aug
  2. 2025BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset4 Jul
  3. 2025Evaluating MLLMs with Multimodal Multi-image Reasoning Benchmark4 Jun
  4. 2025MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos4 Jun
  5. 2025MiMo-VL Technical Report4 Jun
  6. 2025MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs27 May
  7. 2025MMLU-Reason: Benchmarking Multi-Task Multi-modal Language Understanding and Reasoning22 May
  8. 2025Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning12 May
  9. 2025VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge14 Apr
  10. 2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning10 Apr
  11. 2025Kimi-VL Technical Report10 Apr
  12. 2025Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought8 Apr
8 more
  1. 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles21 Mar
  2. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization13 Mar
  3. 2025VisualPRM: An Effective Process Reward Model for Multimodal Reasoning13 Mar
  4. 2025MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning10 Mar
  5. 2025MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency13 Feb
  6. 2025InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model21 Jan
  7. 2024CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes1 Apr
  8. 2023See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning12 Jan

Other references · 15

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  5. 2025Gemma 3 Technical Reportcited by 1,686
  6. 2025s1: Simple test-time scalingcited by 1,311
  7. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
  8. 2025MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligencecited by 169
  9. 2025ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Modelscited by 110
  10. 2018RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipescited by 74
  11. 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotationscited by 53
  12. 2025Kwai Keye-VL Technical Reportcited by 47
3 more
  1. 2024Lost in Time: A New Temporal Benchmark for VideoLLMscited by 36
  2. 2025Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferencescited by 11
  3. 2025Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modelingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  2. 2026Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learningcited by 2
  3. 2026TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videoscited by 1
  4. 2026SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMscited by 1
  5. 2026Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combinecited by 0
  6. 2026Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Modelscited by 0
  7. 2026Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessmentcited by 0
  8. 2026Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models
  2. 2024MM-InstructEval: Zero-Shot Evaluation of (Multimodal) Large Language Models on Multimodal Reasoning Tasks
  3. 2025MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models
  4. 2024MMR: Evaluating Reading Ability of Large Multimodal Models
  5. 2025MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models
  6. 2025Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
  7. 2024Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
  8. 2026Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory