mlsanityData to 14 Oct 2026

Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study

arXiv 2502.11514 ↗First posted 17 Feb 2025cs.CLcited by 11

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Recently, inference-time scaling of chain-of-thought (CoT) has been demonstrated as a promising approach for addressing multi-modal reasoning tasks. While existing studies have predominantly centered on text-based thinking, the integration of both visual and textual modalities within the reasoning process remains unexplored. In this study, we pioneer the exploration of inference-time scaling with multi-modal thought, aiming to bridge this gap. To provide a comprehensive analysis, we systematically investigate popular sampling-based and tree search-based inference-time scaling methods on 10 challenging tasks spanning various domains. Besides, we uniformly adopt a consistency-enhanced verifier to ensure effective guidance for both methods across different thought paradigms. Results show that multi-modal thought promotes better performance against conventional text-only thought, and blending the two types of thought fosters more diverse thinking. Despite these advantages, multi-modal thoughts necessitate higher token consumption for processing richer visual inputs, which raises concerns in practical applications. We hope that our findings on the merits and drawbacks of this research line will inspire future works in the field.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 28 of its 66 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

28 of 66 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model21 Jan
  2. 2024Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension4 Dec
  3. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Step15 Nov
  4. 2024Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models13 Jun
  5. 2024Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models22 May
  6. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct

Other references · 22

  1. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  2. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  4. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
  5. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 480
  6. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 441
  7. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Modelscited by 290
  8. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  9. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 175
  10. 2024LLaVA-Critic: Learning to Evaluate Multimodal Modelscited by 134
  11. 2024RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthinesscited by 131
  12. 2025Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thoughtcited by 109
10 more
  1. 2024OpenR: An Open Source Framework for Advanced Reasoning with Large Language Modelscited by 94
  2. 2025Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Modelcited by 62
  3. 2024IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representationscited by 38
  4. 2024LiteSearch: Efficacious Tree Search for LLMcited by 31
  5. 2024FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compressioncited by 22
  6. 2023No Train Still Gain. Unleash Mathematical Reasoning of Large Language Models with Monte Carlo Tree Search Guided by Energy Functioncited by 20
  7. 2025Enhancing Reasoning through Process Supervision with Monte Carlo Tree Searchcited by 14
  8. 2025Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfallscited by 13
  9. 2024Efficient Multi-modal Large Language Models via Visual Token Groupingcited by 9
  10. 2024LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Informationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 3.

11 papers.

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  2. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 90
  3. 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Modelscited by 44
  4. 2025UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddingscited by 38
  5. 2025Mind with Eyes: from Language Reasoning to Multimodal Reasoningcited by 22
  6. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 14
  7. 2026Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimizationcited by 7
  8. 2025Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaborationcited by 5
  9. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  10. 2026FluxLite: Inference-Time Proposal Control for Discrete Diffusion Modelscited by 1
  11. 2026Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones
  2. 2025Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
  3. 2026Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
  4. 2026CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
  5. 2025Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought
  6. 2024AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning
  7. 2024M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought
  8. 2025ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning