Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In this work, we investigate multimodal meta-verification, which leverages verifier-generated rationales rather than decision-only signals, and explore how to effectively incorporate meta-verification feedback into multimodal verifier training. We identify two key findings. First, symbolic verifier outputs (e.g., bounding boxes) outperform textual explanations as meta-verification rationales, enabling efficient rule-based reinforcement learning rewards while avoiding reliance on model-based rewards from auxiliary judge models. Second, decoupling reinforcement learning objectives for binary judgment and meta-verification substantially outperforms joint reward optimization, due to intrinsic differences in output structure and learning dynamics. Based on these insights, we train OmniVerifier-M1, a generalist visual verifier leveraging symbolic meta-verification and decoupled reinforcement learning. OmniVerifier-M1 provides robust verification and fine-grained error localization, and further enables M1-TTS, a verifier-driven agentic generation system achieving dynamic region-level self-correction. This approach paves the way for more reliable, interpretable, and fine-grained multimodal verification, supporting safer and more controllable foundation model deployment.

翻译：视觉输出日益成为多模态大语言模型的核心，使得可靠且细粒度的验证对于扩展通用基础模型至关重要。本文研究多模态元验证——利用验证器生成的推理依据而非仅依赖决策信号——并探索如何将元验证反馈有效整合到多模态验证器训练中。我们识别出两项关键发现。首先，符号化验证器输出（如边界框）作为元验证推理依据优于文本解释，能够在避免依赖辅助评判模型基于模型的奖励的同时，实现高效的基于规则的强化学习奖励。其次，将二元判断与元验证的强化学习目标解耦，由于输出结构与学习动态的内在差异，其表现显著优于联合奖励优化。基于这些见解，我们训练了OmniVerifier-M1——一种利用符号化元验证与解耦强化学习的通用视觉验证器。OmniVerifier-M1提供稳健的验证与细粒度错误定位，并进一步支撑M1-TTS——一种实现动态区域级自校正的验证器驱动智能生成系统。该方法为更可靠、可解释且细粒度的多模态验证铺平道路，支持更安全且可控的基础模型部署。