mlsanityData to 7 Oct 2026

Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)

arXiv 2504.03151 ↗First posted 4 Apr 2025cs.CL cs.LGcited by 23

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic domains. However, effectively extending these capabilities into multimodal contexts-where models must integrate both visual and textual inputs-continues to be a significant challenge. Multimodal reasoning introduces complexities, such as handling conflicting information across modalities, which require models to adopt advanced interpretative strategies. Addressing these challenges involves not only sophisticated algorithms but also robust methodologies for evaluating reasoning accuracy and coherence. This paper offers a concise yet insightful overview of reasoning techniques in both textual and multimodal LLMs. Through a thorough and up-to-date comparison, we clearly formulate core reasoning challenges and opportunities, highlighting practical methods for post-training optimization and test-time inference. Our work provides valuable insights and guidance, bridging theoretical frameworks and practical implementations, and sets clear directions for future research.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 125 of its 152 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

125 of 152 references.

Closest ancestors · 47

Same direction, newest first

  1. 2025VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity14 Mar
  2. 2025GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training11 Mar
  3. 2025Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?8 Mar
  4. 2025Visual-RFT: Visual Reinforcement Fine-Tuning3 Mar
  5. 2025RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception31 Jan
  6. 2025Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step23 Jan
  7. 2025ReasVQA: Advancing VideoQA with Imperfect Reasoning Process23 Jan
  8. 2025InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model21 Jan
  9. 2025Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!18 Jan
  10. 2025Imagine while Reasoning in Space: Multimodal Visualization-of-Thought13 Jan
  11. 2025Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs11 Jan
  12. 2025Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark9 Jan
35 more
  1. 2025Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning9 Jan
  2. 2025SMIR: Efficient Synthetic Data Pipeline To Improve Multi-Image Reasoning7 Jan
  3. 2025Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild6 Jan
  4. 2025Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?5 Jan
  5. 2024Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning18 Dec
  6. 2024CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models17 Dec
  7. 2024Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension4 Dec
  8. 2024VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning3 Dec
  9. 2024Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination15 Nov
  10. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Step15 Nov
  11. 2024Vision-Language Models Can Self-Improve Reasoning via Reflection30 Oct
  12. 2024Natural Language Inference Improves Compositionality in Vision-Language Models29 Oct
  13. 2024Improve Vision Language Model Chain-of-thought Reasoning21 Oct
  14. 2024Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning4 Oct
  15. 2024JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images19 Sep
  16. 2024LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts6 Jul
  17. 2024Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge5 Jul
  18. 2024Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering3 Jul
  19. 2024From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis28 Jun
  20. 2024ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos27 Jun
  21. 2024Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies16 Jun
  22. 2024ReMI: A Dataset for Reasoning with Multiple Images13 Jun
  23. 2024ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs12 Jun
  24. 2024VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos29 May
  25. 2024WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning6 May
  26. 2024EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning22 Apr
  27. 2024MoReVQA: Exploring Modular Reasoning Models for Video Question Answering9 Apr
  28. 2024Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering5 Apr
  29. 2024CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes1 Apr
  30. 2024Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning25 Mar
  31. 2024VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding21 Mar
  32. 2024HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning19 Mar
  33. 2024CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples20 Feb
  34. 2024ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling9 Feb
  35. 2023Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models5 Dec

Other references · 78

  1. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  2. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 679
  3. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 529
  4. 2023V*: Guided Visual Search as a Core Mechanism in Multimodal LLMscited by 459
  5. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  6. 2023What's "up" with vision-language models? Investigating their struggle with spatial reasoningcited by 245
  7. 2024STAR: A Benchmark for Situated Reasoning in Real-World Videoscited by 213
  8. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 171
  9. 2024Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Modelscited by 151
  10. 2024Direct Preference Optimization of Video Large Multimodal Models from Language Model Rewardcited by 145
  11. 2024LLaVA-Critic: Learning to Evaluate Multimodal Modelscited by 132
  12. 2023Silkie: Preference Distillation for Large Visual Language Modelscited by 128
38 more
  1. 2025R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learningcited by 99
  2. 2023Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revisioncited by 96
  3. 2024Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Modelscited by 90
  4. 2024LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoningcited by 90
  5. 2024VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Modelscited by 85
  6. 2024A Survey on Benchmarks of Multimodal Large Language Modelscited by 81
  7. 2024VideoVista: A Versatile Benchmark for Video Understanding and Reasoningcited by 72
  8. 2024Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Modelscited by 72
  9. 2023Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuningcited by 63
  10. 2023PerceptionGPT: Effectively Fusing Visual Perception into LLMcited by 59
  11. 2024MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilitiescited by 57
  12. 2024VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignmentcited by 56
  13. 2024Reconstructive Visual Instruction Tuningcited by 54
  14. 2024VCA: Video Curious Agent for Long Video Understandingcited by 54
  15. 2023Visual In-Context Promptingcited by 52
  16. 2023Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Modelcited by 52
  17. 2024Making Large Language Models Better Planners with Reasoning-Decision Alignmentcited by 51
  18. 2024CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMscited by 49
  19. 2024Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMscited by 48
  20. 2024Multimodal Latent Language Modeling with Next-Token Diffusioncited by 47
  21. 2024Grounded Multi-Hop VideoQA in Long-Form Egocentric Videoscited by 43
  22. 2023VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generationcited by 41
  23. 2024m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Taskscited by 38
  24. 2024OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquercited by 34
  25. 2024Unveiling Visual Perception in Language Models: An Attention Head Analysis Approachcited by 34
  26. 2024PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chaincited by 29
  27. 2024Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referringcited by 29
  28. 2024FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learningcited by 26
  29. 2024Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramidcited by 26
  30. 2024Exploring Perceptual Limitation of Multimodal Large Language Modelscited by 24
  31. 2024Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervisioncited by 24
  32. 2024GiT: Towards Generalist Vision Transformer through Universal Language Interfacecited by 23
  33. 2024Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoningcited by 23
  34. 2024MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perceptioncited by 21
  35. 2024ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Modelscited by 21
  36. 2024FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehensioncited by 20
  37. 2023Mitigating Open-Vocabulary Caption Hallucinationscited by 18
  38. 2024VLRM: Vision-Language Models act as Reward Models for Image Captioningcited by 18

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 19; 2026: 4.

23 papers.

Sort:

By area:

  1. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 114
  2. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  3. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 49
  4. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 31
  5. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  6. 2025VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoningcited by 26
  7. 2025From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Modelscited by 26
  8. 2025VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuningcited by 24
  9. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  10. 2025MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustnesscited by 5
  11. 2025Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimizationcited by 5
  12. 2025Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neurosciencecited by 3
11 more
  1. 2025Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarkscited by 2
  2. 2025When to Think and When to Look: Uncertainty-Guided Lookbackcited by 2
  3. 2026LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videoscited by 2
  4. 2025MSA at ImageCLEF 2025 Multimodal Reasoning: Multilingual Multimodal Reasoning With Ensemble Vision Language Modelscited by 1
  5. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  6. 2025FADE: Adversarial Concept Erasure in Flow Modelscited by 0
  7. 2025A2R2: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinementcited by 0
  8. 2025ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answeringcited by 0
  9. 2025Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustnesscited by 0
  10. 2026CPPO: Contrastive Perception Policy Optimization for VLM Agentscited by 0
  11. 2026SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning
  2. 2022Towards Reasoning in Large Language Models: A Survey
  3. 2024A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges
  4. 2025Mind with Eyes: from Language Reasoning to Multimodal Reasoning
  5. 2025MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models
  6. 2025Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMs
  7. 2025Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
  8. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey