DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning

• URL: http://arxiv.org/abs/2505.20241v2
• Date: Wed, 04 Jun 2025 20:51:17 GMT
• Title: DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning
• Authors: Qi Cao, Ruiyi Wang, Ruiyi Zhang, Sai Ashish Somayajula, Pengtao Xie,
• Abstract summary: We introduce DreamPRM, a domain-reweighted training framework for multimodal PRMs.<n>In the lower-level optimization, DreamPRM performs fine-tuning on multiple datasets with domain weights.<n>In the upper-level optimization, the PRM is evaluated on a separate meta-learning dataset.
• Score: 33.574626079343936
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reasoning has improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) offer a fine-grained evaluation of intermediate reasoning steps and guide the reasoning process. However, extending PRMs to multimodal large language models (MLLMs) introduces challenges. Since multimodal reasoning covers a wider range of tasks compared to text-only scenarios, the resulting distribution shift from the training to testing sets is more severe, leading to greater generalization difficulty. Training a reliable multimodal PRM, therefore, demands large and diverse datasets to ensure sufficient coverage. However, current multimodal reasoning datasets suffer from quality imbalance, which degrades PRM performance and highlights the need for data selection strategy. To address the issues, we introduce DreamPRM, a domain-reweighted training framework for multimodal PRMs which employs bi-level optimization. In the lower-level optimization, DreamPRM performs fine-tuning on multiple datasets with domain weights, allowing the PRM to prioritize high-quality reasoning signals and alleviating the impact of dataset quality imbalance. In the upper-level optimization, the PRM is evaluated on a separate meta-learning dataset; this feedback updates the domain weights through an aggregation loss function, thereby improving the generalization capability of trained PRM. Extensive experiments on multiple multimodal reasoning benchmarks covering both mathematical and general reasoning show that test-time scaling with DreamPRM consistently improves performance of state-of-the-art MLLMs. Further comparisons reveal that DreamPRM's domain-reweighting strategy surpasses data selection methods and yields higher accuracy gains than existing test-time scaling approaches. Codes are available at https://github.com/coder-qicao/DreamPRM.

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)
• Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning [10.227089771963943]
  We propose an uncertainty-driven framework for automated process reward data construction.<n>We introduce two generic uncertainty-aware output aggregation methods: Hybrid Majority Reward Vote and weighted Reward Frequency Vote.<n>Experiments on ProcessBench, MATH, and GSMPlus show the effectiveness and efficiency of the proposed PRM data construction framework.
  arXiv  Detail & Related papers  (2025-08-03T14:14:13Z)
• Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning [71.3533541927459]
  We propose a novel data selection paradigm termed Activation Reasoning Potential (RAP)<n>RAP identifies cognitive samples by estimating each sample's potential to stimulate genuine multi-modal reasoning.<n>Our RAP method consistently achieves superior performance using only 9.3% of the training data, while reducing computational costs by over 43%.
  arXiv  Detail & Related papers  (2025-06-05T08:40:24Z)
• Discriminative Policy Optimization for Token-Level Reward Models [55.98642069903191]
  Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs)<n>Q-RM explicitly learns token-level Q-functions from preference data without relying on fine-grained annotations.<n>Reinforcement learning with Q-RM significantly enhances training efficiency, achieving convergence 12 times faster than ORM on GSM8K and 11 times faster than step-level PRM on MATH.
  arXiv  Detail & Related papers  (2025-05-29T11:40:34Z)
• From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling [32.72867198629561]
  We investigate the interplay between pre-training and reward model training FLOPs to assess their influence on PRM efficiency and accuracy.<n>Our findings indicate that PRMs trained on mathematical datasets exhibit performance comparable to those tailored for code generation.
  arXiv  Detail & Related papers  (2025-05-24T12:44:15Z)
• MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision [27.571090189791303]
  We propose MM-PRM, a process reward model trained within a fully automated, scalable framework.<n>We first build MM-Policy, a strong multimodal model trained on diverse mathematical reasoning data.<n>We generate over 700k step-level annotations without human labeling.
  arXiv  Detail & Related papers  (2025-05-19T17:55:08Z)
• R-PRM: Reasoning-Driven Process Reward Modeling [53.06844294668382]
  Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step.<n>Existing PRMs typically output evaluation scores directly, limiting both learning efficiency and evaluation accuracy.<n>We propose Reasoning-Driven Process Reward Modeling (R-PRM)<n>R-PRM generates seed data from limited annotations, effectively bootstrapping our model's reasoning capabilities.
  arXiv  Detail & Related papers  (2025-03-27T09:23:08Z)
• Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models [33.547353090281284]
  We propose a novel reward model approach called the Hierarchical Reward Model.<n>It evaluates both individual and consecutive reasoning steps at both fine-grained and coarse-grained levels.<n>It excels at assessing multi-step reasoning coherence, especially when flawed steps are later corrected through self-reflection.
  arXiv  Detail & Related papers  (2025-03-16T15:18:40Z)
• VisualPRM: An Effective Process Reward Model for Multimodal Reasoning [76.35753243272521]
  We introduce VisualPRM, which improves the reasoning abilities of existing Multimodal Large Language Models (MLLMs)<n>Our model achieves a 5.9-point improvement across seven multimodal reasoning benchmarks.<n>For the evaluation of multimodal PRMs, we propose VisualProcessBench, a benchmark with human-annotated step-wise correctness labels.
  arXiv  Detail & Related papers  (2025-03-13T12:03:37Z)
• The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models [31.81567038783558]
  Multimodal Reward Models (MM-RMs) are crucial for aligning Large Language Models (LLMs) with human preferences.<n> MM-RMs often struggle to generalize to out-of-distribution data due to their reliance on unimodal spurious correlations.<n>We introduce a Shortcut-aware MM-RM learning algorithm that mitigates this issue by dynamically reweighting training samples.
  arXiv  Detail & Related papers  (2025-03-05T02:37:41Z)
• Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning [32.850036320802474]
  We introduce Retrieval-Augmented Process Reward Model (RetrievalPRM), a novel framework designed to tackle OOD issues.<n>By utilizing a two-stage retrieval-enhanced mechanism, RetrievalPRM retrieves semantically similar questions and steps as a warmup.<n>Our experiments demonstrate that RetrievalPRM outperforms existing baselines across multiple real-world datasets.
  arXiv  Detail & Related papers  (2025-02-20T08:40:09Z)
• MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
  multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks.<n>Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales.<n>We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
  arXiv  Detail & Related papers  (2024-12-06T18:14:24Z)
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning [71.2981957820888]
  We propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets. The framework initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. The generated data undergo a rigorous evaluation using a dual-model method that assesses both difficulty and quality.
  arXiv  Detail & Related papers  (2024-11-21T02:30:53Z)
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization [65.64108848398696]
  We introduce a preference optimization (PO) process to enhance the multimodal reasoning capabilities of MLLMs.<n>Specifically, we design an automated preference data construction pipeline to create MMPR, a high-quality, large-scale multimodal reasoning preference dataset.<n>We explore integrating PO with MLLMs, developing a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-11-15T18:59:27Z)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)

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.