OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration
This work addresses the need for reliable and interpretable verification in multimodal large language models, which is crucial for safe deployment of generalist foundation models.
The paper introduces OmniVerifier-M1, a multimodal verifier that uses symbolic outputs (bounding boxes) and decoupled reinforcement learning to achieve robust verification and fine-grained error localization. The approach enables a verifier-driven agentic generation system (M1-TTS) for dynamic region-level self-correction.
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.