Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning

TL;DR

Omni-AutoThink introduces an adaptive multimodal reasoning framework that dynamically adjusts reasoning depth based on task difficulty, improving performance across various modalities through reinforcement learning and fine-tuning.

Contribution

The paper presents a novel adaptive reasoning framework with a two-stage training process and a comprehensive multimodal reasoning benchmark, advancing flexible reasoning in Omni models.

Findings

Significant improvement in adaptive reasoning performance over baselines

Effective dynamic adjustment of reasoning depth based on task complexity

Benchmark covering multiple modalities for training and evaluation

Abstract

Recent advances in Omni models have enabled unified multimodal perception and generation. However, most existing systems still exhibit rigid reasoning behaviors, either overthinking simple problems or failing to reason when necessary. To address this limitation, we propose Omni-AutoThink, a novel adaptive reasoning framework that dynamically adjusts the model's reasoning depth according to task difficulty. Our framework comprises two stages: (1) an Adaptive Supervised Fine-Tuning (Adaptive SFT) stage, which endows the Omni model with fundamental reasoning capability using large-scale reasoning-augmented data, and (2) an Adaptive Reinforcement Learning (Adaptive GRPO) stage, which optimizes reasoning behaviors based on task complexity and reward feedback. We further construct a comprehensive adaptive reasoning benchmark that spans text-only, text-audio, text-visual, and text-audio-visual modalities, providing both training and evaluation splits for multimodal reasoning assessment. Experimental results demonstrate that our proposed framework significantly improves adaptive reasoning performance compared to previous baselines. All benchmark data and code will be publicly released.