mlsanityData to 14 Oct 2026

Visual Attention Reasoning via Hierarchical Search and Self-Verification

arXiv 2510.18619 ↗First posted 21 Oct 2025cs.AIcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We propose Visual Attention Reasoning (VAR), a reinforcement learning framework that reformulates reasoning as a hierarchical search with self-verification. VAR enforces traceable evidence grounding by generating explicit bounding boxes, guided by a novel reward function combining geometric precision and semantic sufficiency. Furthermore, it replaces linear Chain-of-Thought with a tree-search policy capable of backtracking to correct logical errors. Theoretical analysis validates the framework's reliability, and extensive experiments demonstrate that VAR significantly outperforms state-of-the-art methods on complex hallucination and safety benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 48 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

34 of 48 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward8 Jun
  2. 2025Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning21 May
  3. 2025Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs21 May
  4. 2025Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning20 May
  5. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning20 May
  6. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model10 Apr
  7. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL10 Mar
  8. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models9 Mar

Other references · 26

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2023Qwen Technical Reportcited by 3,344
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  5. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  7. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
  8. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  9. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  10. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 445
  11. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 357
  12. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
14 more
  1. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 301
  2. 2025Spurious Rewards: Rethinking Training Signals in RLVRcited by 209
  3. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 93
  4. 2025Reward Shaping to Mitigate Reward Hacking in RLHFcited by 88
  5. 2025More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Modelscited by 86
  6. 2024SafeBench: A Safety Evaluation Framework for Multimodal Large Language Modelscited by 69
  7. 2025Are Reasoning Models More Prone to Hallucination?cited by 64
  8. 2024VLSBench: Unveiling Visual Leakage in Multimodal Safetycited by 63
  9. 2024Multimodal Situational Safetycited by 58
  10. 2025ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learningcited by 43
  11. 2022Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQAcited by 30
  12. 2025See or Recall: A Sanity Check for the Role of Vision in Solving Visualization Question Answer Tasks with Multimodal LLMscited by 7
  13. 2025When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Modelscited by 4
  14. 2025Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Modelscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs
  2. 2025Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information
  3. 2026Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification
  4. 2026Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
  5. 2026See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs
  6. 2026Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models
  7. 2026Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration
  8. 2024Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination