mlsanityData to 14 Oct 2026

Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning

arXiv 2606.08231 ↗First posted 6 Jun 2026cs.CVcited by 0

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Test-time Scaling (TTS) has emerged as a pivotal research direction for enhancing model performance by dynamically allocating computational resources during inference. Recent advancements have adapted this paradigm to Multimodal Foundation Models (MFMs), unlocking their potential in multimodal reasoning and generation. Despite rapid progress, the field lacks a systematic survey and unified theoretical framework to delineate the developmental landscape of multimodal TTS. To bridge this gap, we present the first comprehensive review of TTS research for MFMs, proposing a unified taxonomic framework that categorizes existing methodologies into three distinct strategies: sampling-based, feedback-based, and search-based approaches. We further summarize representative applications and benchmarks commonly utilized to evaluate multimodal TTS capabilities in generation and reasoning tasks. Finally, this survey discusses open challenges and outlines future research directions, providing a systematic roadmap for subsequent studies in this rapidly evolving field.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 78 of its 121 references that are in the map. First posted on arXiv 6 Jun 2026.

Builds on

78 of 121 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Can Test-Time Scaling Improve World Foundation Model?31 Mar
  2. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?31 Mar
  3. 2025Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning26 Jan
  4. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning5 Jan
  5. 2024Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models18 Dec
  6. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions21 Nov
  7. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  8. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models1 Aug
  9. 2024V-STaR: Training Verifiers for Self-Taught Reasoners9 Feb

Other references · 69

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  8. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  9. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  10. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 872
  11. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
  12. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 567
38 more
  1. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 495
  2. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  3. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 441
  4. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 378
  5. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 327
  6. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 315
  7. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?cited by 286
  8. 2025ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Usecited by 254
  9. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  10. 2025Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videoscited by 236
  11. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Stepscited by 234
  12. 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understandingcited by 224
  13. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 175
  14. 2025SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformercited by 165
  15. 2024DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Modelscited by 146
  16. 2025VisualPRM: An Effective Process Reward Model for Multimodal Reasoningcited by 139
  17. 2025From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3Dcited by 138
  18. 2025Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Stepcited by 131
  19. 2024SAT: Dynamic Spatial Aptitude Training for Multimodal Language Modelscited by 114
  20. 2025GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoningcited by 97
  21. 2024CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understandingcited by 85
  22. 2025ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agentscited by 66
  23. 2025VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perceptioncited by 65
  24. 2025RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Modelscited by 61
  25. 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoningcited by 50
  26. 2025Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflectioncited by 43
  27. 2025Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Searchcited by 41
  28. 2025Video-T1: Test-Time Scaling for Video Generationcited by 40
  29. 2025Scaling Image and Video Generation via Test-Time Evolutionary Searchcited by 40
  30. 2025Dynamic Search for Inference-Time Alignment in Diffusion Modelscited by 37
  31. 2025VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Searchcited by 36
  32. 2025METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scalingcited by 34
  33. 2025Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoningcited by 33
  34. 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generationcited by 32
  35. 2025DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoningcited by 31
  36. 2025Test-Time Scaling of Diffusion Models via Noise Trajectory Searchcited by 30
  37. 2025VideoGen-Eval: Agent-based System for Video Generation Evaluationcited by 23
  38. 2025Verifier-free Test-Time Sampling for Vision-Language-Action Modelscited by 23

50 most cited of 69 All 69 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025The Art of Scaling Test-Time Compute for Large Language Models
  2. 2026UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
  3. 2025Limits and Gains of Test-Time Scaling in Vision-Language Reasoning
  4. 2026Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
  5. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
  6. 2026Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
  7. 2025Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
  8. 2025Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning