R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

🤗 Upvotes: 84 | cs.CV, cs.AI, cs.LG

Authors:
Jie Jiang, Qi Yang, Bolin Ni, Shiming Xiang, Han Hu, Houwen Peng

Title:
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

Arxiv:
http://arxiv.org/abs/2508.21113v1

Abstract:
Multimodal Large Language Models (MLLMs) equipped with step-by-step thinking capabilities have demonstrated remarkable performance on complex reasoning problems. However, this thinking process is redundant for simple problems solvable without complex reasoning. To address this inefficiency, we propose R-4B, an auto-thinking MLLM, which can adaptively decide when to think based on problem complexity. The central idea of R-4B is to empower the model with both thinking and non-thinking capabilities using bi-mode annealing, and apply Bi-mode Policy Optimization~(BPO) to improve the model's accuracy in determining whether to activate the thinking process. Specifically, we first train the model on a carefully curated dataset spanning various topics, which contains samples from both thinking and non-thinking modes. Then it undergoes a second phase of training under an improved GRPO framework, where the policy model is forced to generate responses from both modes for each input query. Experimental results show that R-4B achieves state-of-the-art performance across 25 challenging benchmarks. It outperforms Qwen2.5-VL-7B in most tasks and achieves performance comparable to larger models such as Kimi-VL-A3B-Thinking-2506 (16B) on reasoning-intensive benchmarks with lower computational cost.