mlsanityData to 7 Oct 2026

MM-THEBench: Do Reasoning MLLMs Think Reasonably?

arXiv 2601.22735 ↗First posted 30 Jan 2026cs.CLcited by 1

On the map: LLM reasoning → Hallucination detection and mitigation

also in 1 more
Abstract (arXiv)

Recent advances in multimodal large language models (MLLMs) mark a shift from non-thinking models to post-trained reasoning models capable of solving complex problems through thinking. However, whether such thinking mitigates hallucinations in multimodal perception and reasoning remains unclear. Self-reflective reasoning enhances robustness but introduces additional hallucinations, and subtle perceptual errors still result in incorrect or coincidentally correct answers. Existing benchmarks primarily focus on models before the emergence of reasoning MLLMs, neglecting the internal thinking process and failing to measure the hallucinations that occur during thinking. To address these challenges, we introduce MM-THEBench, a comprehensive benchmark for assessing hallucinations of intermediate CoTs in reasoning MLLMs. MM-THEBench features a fine-grained taxonomy grounded in cognitive dimensions, diverse data with verified reasoning annotations, and a multi-level automated evaluation framework. Extensive experiments on mainstream reasoning MLLMs reveal insights into how thinking affects hallucination and reasoning capability in various multimodal tasks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 52 of its 72 references that are in the map. First posted on arXiv 30 Jan 2026.

Builds on

52 of 72 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM30 May
  2. 2025Are Reasoning Models More Prone to Hallucination?29 May
  3. 2025More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models23 May

Other references · 49

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2025Qwen2.5-VL Technical Reportcited by 5,418
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  6. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  7. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  8. 2024A Survey on LLM-as-a-Judgecited by 1,384
  9. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  10. 2024OpenAI o1 System Cardcited by 1,220
  11. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  12. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 580
37 more
  1. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 501
  2. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  3. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 439
  4. 2024LVBench: An Extreme Long Video Understanding Benchmarkcited by 402
  5. 2025Seed1.5-VL Technical Reportcited by 367
  6. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalizationcited by 364
  7. 2025Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscationcited by 338
  8. 2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learningcited by 315
  9. 2025Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videoscited by 225
  10. 2025Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetycited by 222
  11. 2025SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Modelscited by 209
  12. 2025Chain-of-Thought Reasoning In The Wild Is Not Always Faithfulcited by 166
  13. 2025SpaceR: Reinforcing MLLMs in Video Spatial Reasoningcited by 152
  14. 2025MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiencycited by 123
  15. 2025OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignmentcited by 118
  16. 2025Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMscited by 115
  17. 2025Reinforcement Learning with Rubric Anchorscited by 108
  18. 2025OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Modelscited by 105
  19. 2025ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agentscited by 80
  20. 2025MM-RLHF: The Next Step Forward in Multimodal LLM Alignmentcited by 79
  21. 2025Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thoughtcited by 69
  22. 2024MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilitiescited by 57
  23. 2025ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Modelscited by 56
  24. 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learningcited by 53
  25. 2024Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoningcited by 50
  26. 2025Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Rewardcited by 45
  27. 2024Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidancecited by 44
  28. 2025VerIF: Verification Engineering for Reinforcement Learning in Instruction Followingcited by 43
  29. 2024Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignmentcited by 42
  30. 2024Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucinationcited by 29
  31. 2025More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Modelscited by 26
  32. 2025VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelitycited by 23
  33. 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Modelscited by 22
  34. 2025R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learningcited by 18
  35. 2025RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputscited by 16
  36. 2025Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbationscited by 7
  37. 2025Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Modelscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Beyond Fluency: Toward Reliable Trajectories in Agentic IRcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning
  2. 2026Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
  3. 2025The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
  4. 2025Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
  5. 2026HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
  6. 2026Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization
  7. 2025Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
  8. 2024Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate