UniCAR-RL: Seeing Better before Thinking Deeper in Visual Mathematics

2026-09-12

AI Summary

本文针对多模态大语言模型在数学视觉推理中的感知与逻辑错误，提出UniCAR-RL框架，通过解耦和优化感知与推理能力来提高模型性能。

Abstract

Multimodal Large Language Models (MLLMs) often struggle with complex mathematical visual reasoning primarily due to a lack of fine-grained perception, causing initial visual hallucinations to directly trigger cascading reasoning failures. In traditional end-to-end reinforcement learning (RL), sparse rewards fail to decouple perceptual hallucinations from logical missteps, hindering targeted perception optimization. Alternatively, fine-tuning with perception-enhanced CoT data incurs high costs and hallucinations. In this paper, we address these challenges by proposing UniCAR-RL, an annotation-free RL framework. By explicitly decoupling the optimization of perception and reasoning during the training process, it achieves isolation and optimization of both capabilities. Specifically, UniCAR-RL consists of three synergistic branches: 1) a Caption-RL branch that optimizes perception capabilities through verifier-guided reasoning validation; 2) a Reasoning-RL branch that performs logical reasoning based on a gold image description to halt cascading errors; 3) a QA-RL branch that retains native end-to-end alignment to ensure robust question-answering performance. Experiments show that UniCAR-RL substantially improves MLLMs' mathematical and visual reasoning using only raw short-answer data. Furthermore, it demonstrates strong generalization across diverse architectures and scales.

Problem

• Multimodal Large Language Models
• visual reasoning
• perceptual hallucinations
• reinforcement learning
• fine-grained perception

Innovation

• UniCAR-RL
• perception and reasoning decoupling
• reinforcement learning
• visual mathematics
• multimodal large language models