VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning

TL;DR

VL-Cogito introduces a multi-stage curriculum reinforcement learning framework that systematically enhances multimodal reasoning in large language models, leading to improved performance across diverse complex tasks.

Contribution

The paper presents VL-Cogito, a novel multimodal reasoning model trained with a progressive curriculum RL framework featuring dynamic difficulty adjustment and reasoning path regulation.

Findings

VL-Cogito outperforms existing models on multimodal benchmarks.

The multi-stage curriculum improves reasoning stability and accuracy.

Dynamic mechanisms balance reasoning efficiency and correctness.

Abstract

Reinforcement learning has proven its effectiveness in enhancing the reasoning capabilities of large language models. Recent research efforts have progressively extended this paradigm to multimodal reasoning tasks. Due to the inherent complexity and diversity of multimodal tasks, especially in semantic content and problem formulations, existing models often exhibit unstable performance across various domains and difficulty levels. To address these limitations, we propose VL-Cogito, an advanced multimodal reasoning model trained via a novel multi-stage Progressive Curriculum Reinforcement Learning (PCuRL) framework. PCuRL systematically guides the model through tasks of gradually increasing difficulty, substantially improving its reasoning abilities across diverse multimodal contexts. The framework introduces two key innovations: (1) an online difficulty soft weighting mechanism, dynamically adjusting training difficulty across successive RL training stages; and (2) a dynamic length reward mechanism, which encourages the model to adaptively regulate its reasoning path length according to task complexity, thus balancing reasoning efficiency with correctness. Experimental evaluations demonstrate that VL-Cogito consistently matches or surpasses existing reasoning-oriented models across mainstream multimodal benchmarks spanning mathematics, science, logic, and general understanding, validating the effectiveness of our approach.