Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning

About

Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on complex multimodal reasoning tasks. We present ARM-Thinker, an A}gentic multimodal Reward Model that autonomously invokes external tools (e.g., image cropping, doc page retrieval) to ground judgments in verifiable evidence, replacing static, non-interactive reward scoring. This enables the model to verify fine-grained visual details, cross-reference multi-page evidence, and validate reasoning claims, which are capabilities absent in existing reward models. We train ARM-Thinker with multi-stage reinforcement learning, jointly optimizing tool-calling decisions and judgment accuracy. To evaluate agentic reward modeling, we introduce ARMBench-VL, comprising three benchmarks that assess fine-grained visual grounding (image-level tools), multi-page document understanding (retrieval tools), and instruction following (text-level verification). ARM-Thinker achieves +16.2% average improvement on reward modeling benchmarks, +9.6% on tool-use tasks, and outperforms baselines on multimodal math and logical reasoning benchmarks. Our results demonstrate that agentic capabilities significantly enhance both accuracy and interpretability of reward models.

Shengyuan Ding, Xinyu Fang, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiangyu Zhao, Haodong Duan, Xiaoyi Dong, Jianze Liang, Bin Wang, Conghui He, Dahua Lin, Jiaqi Wang• 2025

Related benchmarks

TaskDatasetResultRank
Mathematical Multimodal ReasoningMathVista
Accuracy70.2
46
Multimodal ReasoningMMMU
Accuracy57.2
44
Multimodal Math ReasoningMathVision
Accuracy25.9
31
Mathematical Multimodal ReasoningMathVerse
Accuracy41.6
29
Multimodal Math ReasoningWeMath
Accuracy46.1
26
Reward ModelingVLRewardBench (test)
General55.7
24
Multimodal ReasoningLogicVista
Accuracy52.8
24
Visual Tool-UseHRBench 4K
Accuracy80.1
9
Visual Tool-UseHRBench-8K
Accuracy73.7
9
Visual Tool-UseMME RealWorld
Accuracy65.8
9
Showing 10 of 12 rows

Other info

GitHub

Follow for update