StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models

• URL: http://arxiv.org/abs/2508.05383v1
• Date: Thu, 07 Aug 2025 13:31:21 GMT
• Title: StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models
• Authors: Xiangxiang Zhang, Jingxuan Wei, Donghong Zhong, Qi Chen, Caijun Jia, Cheng Tan, Jinming Gu, Xiaobo Qin, Zhiping Liu, Liang Hu, Tong Sun, Yuchen Wu, Zewei Sun, Chenwei Lou, Hua Zheng, Tianyang Zhan, Changbao Wang, Shuangzhi Wu, Zefa Lin, Chang Guo, Sihang Yuan, Riwei Chen, Shixiong Zhao, Yingping Zhang, Gaowei Wu, Bihui Yu, Jiahui Wu, Zhehui Zhao, Qianqian Liu, Ruofeng Tang, Xingyue Huang, Bing Zhao, Mengyang Zhang, Youqiang Zhou,
• Abstract summary: StructVRM is a method that aligns multimodal reasoning with Structured and Verifiable Reward Models.<n>At its core is a model-based verifier trained to provide fine-grained, sub-question-level feedback.<n>Our trained model, Seed-StructVRM, achieves state-of-the-art performance on six out of twelve public multimodal benchmarks and our newly curated, high-difficulty STEM-Bench.
• Score: 25.345348726907854
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanisms, which provide a single binary score for an entire response, are too coarse to guide models through intricate problems with multiple sub-parts. To address this, we introduce StructVRM, a method that aligns multimodal reasoning with Structured and Verifiable Reward Models. At its core is a model-based verifier trained to provide fine-grained, sub-question-level feedback, assessing semantic and mathematical equivalence rather than relying on rigid string matching. This allows for nuanced, partial credit scoring in previously intractable problem formats. Extensive experiments demonstrate the effectiveness of StructVRM. Our trained model, Seed-StructVRM, achieves state-of-the-art performance on six out of twelve public multimodal benchmarks and our newly curated, high-difficulty STEM-Bench. The success of StructVRM validates that training with structured, verifiable rewards is a highly effective approach for advancing the capabilities of multimodal models in complex, real-world reasoning domains.

Related papers

• GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning [12.724393910603299]
  We introduce the Generative Multimodal Process Reward Model (GM-PRM)<n>Instead of a simple scalar score, GM-PRM provides a fine-grained, interpretable analysis of each reasoning step.<n>We show that GM-PRM achieves state-of-the-art results on multiple multimodal math benchmarks.
  arXiv  Detail & Related papers  (2025-08-06T05:10:29Z)
• VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning [69.44871115752055]
  We propose an advanced multimodal reasoning model trained via a novel Progressive Curriculum Reinforcement Learning (PCuRL) framework.<n>PCuRL systematically guides the model through tasks of gradually increasing difficulty, substantially improving its reasoning abilities across diverse multimodal contexts.<n>The framework introduces two key innovations: (1) an online difficulty soft weighting mechanism, dynamically adjusting training difficulty across successive RL training stages; and (2) a dynamic length reward mechanism, which encourages the model to adaptively regulate its reasoning path length according to task complexity.
  arXiv  Detail & Related papers  (2025-07-30T12:23:21Z)
• SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning [26.167394979565454]
  We propose SAM-R1, a novel framework that enables multimodal large models to perform fine-grained reasoning in image understanding tasks.<n>Our approach is the first to incorporate fine-grained segmentation settings during the training of multimodal reasoning models.<n>With only 3k training samples, SAM-R1 achieves strong performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-05-28T17:08:28Z)
• A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models [74.48084001058672]
  The rise of foundation models has transformed machine learning research.<n> multimodal foundation models (MMFMs) pose unique interpretability challenges beyond unimodal frameworks.<n>This survey explores two key aspects: (1) the adaptation of LLM interpretability methods to multimodal models and (2) understanding the mechanistic differences between unimodal language models and crossmodal systems.
  arXiv  Detail & Related papers  (2025-02-22T20:55:26Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning [49.3242278912771]
  We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning) The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs. It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-31T14:23:49Z)
• The Effectiveness of a Simplified Model Structure for Crowd Counting [11.640020969258101]
  This paper discusses how to construct high-performance crowd counting models using only simple structures. We propose the Fuss-Free Network (FFNet) that is characterized by its simple and efficieny structure, consisting of only a backbone network and a multi-scale feature fusion structure. Our proposed crowd counting model is trained and evaluated on four widely used public datasets, and it achieves accuracy that is comparable to that of existing complex models.
  arXiv  Detail & Related papers  (2024-04-11T15:42:53Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• S2RMs: Spatially Structured Recurrent Modules [105.0377129434636]
  We take a step towards exploiting dynamic structure that are capable of simultaneously exploiting both modular andtemporal structures. We find our models to be robust to the number of available views and better capable of generalization to novel tasks without additional training.
  arXiv  Detail & Related papers  (2020-07-13T17:44:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.