CoTZero: Annotation-Free Human-Like Vision Reasoning via Hierarchical Synthetic CoT

2026-02-09

AI Summary

This work proposes a human-like visual reasoning framework that operates without human-annotated data, addressing the limitations of current vision-language models which rely on superficial correlations and lack structured, causal understanding necessary for compositional and verifiable reasoning. Inspired by cognitive science, the approach employs a global-to-local synthesis strategy to generate structured reasoning paths via a two-stage chain-of-thought (CoT) process. It further aligns hierarchical reasoning through reinforcement fine-tuning (RFT) guided by a Cognitive Consistency Verifiable Reward (CCVR) mechanism. Evaluated on a multi-level semantic inconsistency benchmark, the method achieves an F1 score of 83.33%, demonstrating substantial improvements in both in-domain and out-of-domain reasoning performance as well as model interpretability.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Recent advances in vision-language models (VLMs) have markedly improved image-text alignment, yet they still fall short of human-like visual reasoning. A key limitation is that many VLMs rely on surface correlations rather than building logically coherent structured representations, which often leads to missed higher-level semantic structure and non-causal relational understanding, hindering compositional and verifiable reasoning. To address these limitations by introducing human models into the reasoning process, we propose CoTZero, an annotation-free paradigm with two components: (i) a dual-stage data synthesis approach and (ii) a cognition-aligned training method. In the first component, we draw inspiration from neurocognitive accounts of compositional productivity and global-to-local analysis. In the bottom-up stage, CoTZero extracts atomic visual primitives and incrementally composes them into diverse, structured question-reasoning forms. In the top-down stage, it enforces hierarchical reasoning by using coarse global structure to guide the interpretation of local details and causal relations. In the cognition-aligned training component, built on the synthesized CoT data, we introduce Cognitively Coherent Verifiable Rewards (CCVR) in Reinforcement Fine-Tuning (RFT) to further strengthen VLMs'hierarchical reasoning and generalization, providing stepwise feedback on reasoning coherence and factual correctness. Experiments show that CoTZero achieves an F1 score of 83.33 percent on our multi-level semantic inconsistency benchmark with lexical-perturbation negatives, across both in-domain and out-of-domain settings. Ablations confirm that each component contributes to more interpretable and human-aligned visual reasoning.

Problem

• visual reasoning
• vision-language models
• structured representation
• causal relations
• compositional reasoning

Innovation

• annotation-free
• hierarchical reasoning
• synthetic chain-of-thought
• cognitive alignment
• reinforcement fine-tuning