CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving

• URL: http://arxiv.org/abs/2601.01874v1
• Date: Mon, 05 Jan 2026 08:02:18 GMT
• Title: CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
• Authors: Shuhang Chen, Yunqiu Xu, Junjie Xie, Aojun Lu, Tao Feng, Zeying Huang, Ning Zhang, Yi Sun, Yi Yang, Hangjie Yuan,
• Abstract summary: We present CogFlow, a novel cognitive-inspired three-stage framework that incorporates a knowledge internalization stage.<n>To guarantee faithful integration of extracted visual cues into subsequent reasoning, we introduce a Knowledge Internalization Reward model.<n>We also contribute a new dataset MathCog for model training, which contains samples with over 120K high-quality perception-reasoning aligned annotations.
• Score: 28.57547723919984
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reasoning, but their solutions are limited to improving the extraction and interpretation of visual inputs. Notably, they all ignore the key issue of whether the extracted visual cues are faithfully integrated and properly utilized in subsequent reasoning. Motivated by this, we present CogFlow, a novel cognitive-inspired three-stage framework that incorporates a knowledge internalization stage, explicitly simulating the hierarchical flow of human reasoning: perception$\Rightarrow$internalization$\Rightarrow$reasoning. Inline with this hierarchical flow, we holistically enhance all its stages. We devise Synergistic Visual Rewards to boost perception capabilities in parametric and semantic spaces, jointly improving visual information extraction from symbols and diagrams. To guarantee faithful integration of extracted visual cues into subsequent reasoning, we introduce a Knowledge Internalization Reward model in the internalization stage, bridging perception and reasoning. Moreover, we design a Visual-Gated Policy Optimization algorithm to further enforce the reasoning is grounded with the visual knowledge, preventing models seeking shortcuts that appear coherent but are visually ungrounded reasoning chains. Moreover, we contribute a new dataset MathCog for model training, which contains samples with over 120K high-quality perception-reasoning aligned annotations. Comprehensive experiments and analysis on commonly used visual mathematical reasoning benchmarks validate the superiority of the proposed CogFlow.

Related papers

• Toward Cognitive Supersensing in Multimodal Large Language Model [67.15559571626747]
  We introduce Cognitive Supersensing, a training paradigm that endows MLLMs with human-like visual imagery capabilities.<n>In experiments, MLLMs trained with Cognitive Supersensing significantly outperform state-of-the-art baselines on CogSense-Bench.<n>We will open-source the CogSense-Bench and our model weights.
  arXiv  Detail & Related papers  (2026-02-02T02:19:50Z)
• SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving [17.304596904197204]
  Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information.<n>Current models struggle to accurately decompose intricate visual inputs and connect geometric perception with structured reasoning.<n>We propose SpatialMath, a novel Spatial-Infused Reasoning Framework designed to integrate spatial representations into structured symbolic reasoning chains.
  arXiv  Detail & Related papers  (2026-01-24T15:31:20Z)
• Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy [75.66913260900726]
  Reinforcement Learning with Verifiable Rewards has significantly advanced reasoning capabilities in Large Language Models.<n>Existing paradigms, driven by text-centric outcome rewards, encourage models to bypass visual perception.<n>We propose textbfThinking with Deltas, a framework driven by a textbfDifferential Visual Reasoning Policy.
  arXiv  Detail & Related papers  (2026-01-11T08:25:34Z)
• Monet: Reasoning in Latent Visual Space Beyond Images and Language [55.424507246294326]
  "Thinking with images" has emerged as an effective paradigm for advancing visual reasoning.<n>Existing methods fall short of human-like abstract visual thinking.<n>We introduce Monet, a training framework that enables multimodal large language models to reason directly within the latent visual space.
  arXiv  Detail & Related papers  (2025-11-26T13:46:39Z)
• Unleashing Perception-Time Scaling to Multimodal Reasoning Models [60.578179197783754]
  Recent advances in inference-time scaling have substantially enhanced the reasoning capabilities of Large Vision-Language Models (LVLMs)<n>Inspired by this success, similar strategies have been applied to multimodal reasoning, yet their impact on visual perception remains unclear.<n>We propose Perception-Time Scaling (PTS), a novel paradigm that encourages token-rich perception and decomposes complex perception problems into intermediate tractable sub-problems.
  arXiv  Detail & Related papers  (2025-10-10T03:17:52Z)
• Align and Surpass Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning [18.13538667261998]
  Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background.<n>We build a visual system that mimicks human visual camouflaged perception to progressively and iteratively refocus' visual concealed content.
  arXiv  Detail & Related papers  (2025-05-26T07:27:18Z)
• Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning [58.73625654718187]
  Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes.<n>Existing approaches fine-tune the visual backbone by seen-class data to obtain semantic-related visual features.<n>This paper proposes a novel visual and semantic prompt collaboration framework, which utilizes prompt tuning techniques for efficient feature adaptation.
  arXiv  Detail & Related papers  (2025-03-29T10:17:57Z)
• A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs [3.2228025627337864]
  This paper introduces a structured evaluation framework to dissect the perception-reasoning interface in Vision-Language Models (VLMs)<n>We propose three distinct evaluation paradigms, mirroring human problem-solving strategies.<n>Applying this framework, we demonstrate that CA, leveraging powerful language models for reasoning over rich, independently generated descriptions, achieves new state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2025-01-23T12:42:42Z)
• Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios [69.00444996464662]
  We propose RIV-CoT, a Retrieval-Based Interleaved Visual Chain-of-Thought method that enables vision-language models to reason using visual crops corresponding to relevant entities.<n>Our experiments demonstrate that RIV-CoT improves answer accuracy by 3.1% and reasoning accuracy by 4.6% over vanilla CoT prompting.
  arXiv  Detail & Related papers  (2025-01-08T18:31:16Z)
• Learning Differentiable Logic Programs for Abstract Visual Reasoning [22.167393386879294]
  Differentiable forward reasoning has been developed to integrate reasoning with gradient-based machine learning paradigms.<n>NEUMANN is a graph-based differentiable forward reasoner, passing messages in a memory-efficient manner and handling structured programs with functors.<n>We demonstrate that NEUMANN solves visual reasoning tasks efficiently, outperforming neural, symbolic, and neuro-symbolic baselines.
  arXiv  Detail & Related papers  (2023-07-03T11:02:40Z)
• Visual Superordinate Abstraction for Robust Concept Learning [80.15940996821541]
  Concept learning constructs visual representations that are connected to linguistic semantics. We ascribe the bottleneck to a failure of exploring the intrinsic semantic hierarchy of visual concepts. We propose a visual superordinate abstraction framework for explicitly modeling semantic-aware visual subspaces.
  arXiv  Detail & Related papers  (2022-05-28T14:27:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.