MG-Thinker：面向多图像推理定位的双轴自反思方法

中文摘要 AI 辅助

强化学习（RL）近期在多模态推理中带来了显著的性能提升，为细粒度视觉感知开辟了一条有前景的路径。然而，对于多图像推理定位（MRG）任务——即在真实世界的多图像情境中进行推理以实现像素级精确定位——现有的基于RL的方法忽视了该范式固有的两个特性：由粗到细的层次化推理模式，以及异构分布的任务-样本难度。在本工作中，我们提出了MG-Thinker，一种后训练RL框架，它推进了一种具有这种层次化推理的新MRG范式，并辅以一个精心整理的包含25K条MRG数据的数据集，该数据集带有任务自适应的思维链（CoT）标注，能够在得出结论前引出多视角证据。为了解决异构的任务-样本难度，我们进一步提出了双轴DAPO（BiA-DAPO），它通过两种互补机制，将rollout优势沿组内信号轴和组间能力轴进行分解，这两种机制均基于我们定义的候选池，以获得稳定的组级统计量。大量实验表明，MG-Thinker在多图像推理定位上达到了最先进的性能，同时持续提升了在多图像理解及多样化多模态基准上的泛化能力。

英文摘要

Reinforcement learning (RL) has recently delivered substantial gains in multimodal reasoning, opening a promising route for fine-grained visual perception. Yet for multi-image reasoning grounding (MRG), reasoning over real-world multi-image contexts toward pixel-precise localization, existing RL-based approaches overlook two characteristics intrinsic to this paradigm: a coarse-to-fine hierarchical reasoning pattern, and heterogeneously distributed task--sample difficulties. In this work, we present MG-Thinker, a post-training RL framework that advances a new MRG paradigm featuring such hierarchical reasoning, supported by a curated 25K MRG dataset with task-adaptive Chain-of-Thought (CoT) annotations that elicit multi-perspective evidence before conclusion. To remedy the heterogeneous task--sample difficulties, we further propose Bi-Axial DAPO (BiA-DAPO), which decomposes rollout advantages along an intra-group signal axis and an inter-group competence axis through two complementary mechanisms, both grounded on our defined candidate pool for stable group-level statistics. Extensive experiments show that MG-Thinker achieves state-of-the-art performance on multi-image reasoning grounding while consistently improving generalization across multi-image understanding and diverse multimodal benchmarks.

发表机构

• Huazhong University of Science and Technology（华中科技大学）
• Tsinghua University（清华大学）

机构由 AI 辅助整理，请以论文原文为准。