The rapid advancement of generative AI has substantially improved image and video synthesis, amplifying the risk of multimodal visual misinformation. Recent MLLMs have shown promise for transparent AI-generated content detection through reasoning and explanation, yet existing approaches largely treat image and video forensics as isolated tasks, leaving cross-modal synergies underexplored. To address this, we present \textbf{BusterX++}, a unified MLLM for joint image and video detection with interpretable reasoning. We also introduce \textbf{GenBuster-Bench++}, a meticulously curated, difficulty-aligned benchmark containing balanced image and video samples spanning recent generation models and diverse real-world scenarios. Using this controlled setting, we revisit the widely adopted $SFT \rightarrow RL$ post-training paradigm. Notably, our findings demonstrate that a single-stage, pure RL strategy driven strictly by sparse outcome rewards consistently matches or surpasses a strong SFT+RL baseline across both unified and single-modality settings. Our key insight reveals that SFT imposes lower policy entropy, which restricts the policy search space and dampens exploratory freedom. In contrast, single-stage pure RL maintains higher policy entropy throughout training, effectively unlocking the spontaneous emergence of cross-modal capability transfer between image and video forensics. Extensive experiments demonstrate that BusterX++ achieves state-of-the-art performance, highlighting the powerful potential of RL for unified cross-modal visual reasoning.

翻译：生成式AI的快速发展显著提升了图像与视频合成质量，同时加剧了多模态视觉虚假信息的风险。近期多模态大语言模型（MLLM）通过推理与解释策略在透明化AI生成内容检测方面展现出潜力，但现有方法仍将图像与视频取证视为独立任务，跨模态协同作用尚未得到充分探索。为此，本文提出**BusterX++**——一种统一的多模态大语言模型，可同时进行图像与视频检测并实现可解释推理。此外，我们构建了**GenBuster-Bench++**基准数据集，该数据集经过精心设计，包含难度对齐的平衡样本，涵盖最新生成模型及多样化真实场景。基于这一受控实验环境，我们重新审视了广泛采用的$SFT \rightarrow RL$后训练范式。值得注意的是，实验表明：采用纯强化学习（RL）策略的单阶段训练——仅依赖稀疏结果奖励——在统一模态与单模态设置下均能稳定达到或超越基于强SFT+RL的基线方法。关键洞察在于，监督微调（SFT）会降低策略熵值，限制策略搜索空间并抑制探索自由度；而单阶段纯RL训练全程维持较高策略熵，有效激发了图像与视频取证间跨模态能力迁移的自发涌现。大量实验证明，BusterX++实现了最先进性能，彰显了RL在统一跨模态视觉推理中的强大潜力。