URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics

• URL: http://arxiv.org/abs/2501.04686v5
• Date: Fri, 23 May 2025 08:57:37 GMT
• Title: URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics
• Authors: Ruilin Luo, Zhuofan Zheng, Yifan Wang, Xinzhe Ni, Zicheng Lin, Songtao Jiang, Yiyao Yu, Chufan Shi, Ruihang Chu, Jin Zeng, Yujiu Yang,
• Abstract summary: Process Reward Models (PRMs) have shown promise in enhancing the mathematical reasoning capabilities of Large Language Models.<n>We take the first step toward unlocking the potential of PRMs in multimodal mathematical reasoning.<n>We introduce URSA, a three-stage Unfolding multimodal Process-Supervision Aided training framework.
• Score: 23.80647785460245
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Process Reward Models (PRMs) have shown promise in enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) through Test-Time Scaling (TTS). However, their integration into multimodal reasoning remains largely unexplored. In this work, we take the first step toward unlocking the potential of PRMs in multimodal mathematical reasoning. We identify three key challenges: (1) the scarcity of high-quality reasoning data constrains the capabilities of foundation Multimodal Large Language Models (MLLMs), which imposes further limitations on the upper bounds of TTS and reinforcement learning (RL); (2) a lack of automated methods for process labeling within multimodal contexts persists; (3) the employment of process rewards in unimodal RL faces issues like reward hacking, which may extend to multimodal scenarios. To address these issues, we introduce URSA, a three-stage Unfolding multimodal Process-Supervision Aided training framework. We first construct MMathCoT-1M, a high-quality large-scale multimodal Chain-of-Thought (CoT) reasoning dataset, to build a stronger math reasoning foundation MLLM, URSA-8B. Subsequently, we go through an automatic process to synthesize process supervision data, which emphasizes both logical correctness and perceptual consistency. We introduce DualMath-1.1M to facilitate the training of URSA-8B-RM. Finally, we propose Process-Supervised Group-Relative-Policy-Optimization (PS-GRPO), pioneering a multimodal PRM-aided online RL method that outperforms vanilla GRPO. With PS-GRPO application, URSA-8B-PS-GRPO outperforms Gemma3-12B and GPT-4o by 8.4% and 2.7% on average across 6 benchmarks. Code, data and checkpoint can be found at https://github.com/URSA-MATH.

Related papers

• MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization [74.04867639197445]
  MiroMind-M1 is a set of fully open-source RLMs built on the Qwen-2.5-based benchmarks.<n>Our models are trained in two stages: SFT on a carefully curated corpus of 719K math-reasoning problems with verified CoT trajectories, followed by RLVR on 62K challenging and verifiable problems.
  arXiv  Detail & Related papers  (2025-07-19T16:21:23Z)
• WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning [17.459985667824807]
  Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise.<n>In this paper, we show how to achieve the general-purpose visual-language reasoning through reinforcement learning.
  arXiv  Detail & Related papers  (2025-06-09T16:20:54Z)
• 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)
• Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning [28.92744927199283]
  ReVisual-R1 achieves a new state-of-the-art among open-source 7B MLLMs on challenging benchmarks including MathVerse, MathVision, WeMath, LogicVista, DynaMath, and challenging AIME2024 and AIME2025.
  arXiv  Detail & Related papers  (2025-06-04T17:51:08Z)
• Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO [25.288796606275973]
  We propose MM-UPT, a simple yet effective framework for unsupervised post-training of MLLMs.<n> MM-UPT builds upon GRPO, replacing traditional reward signals with a self-rewarding mechanism based on majority voting over multiple sampled responses.<n>Our experiments demonstrate that MM-UPT significantly improves the reasoning ability of Qwen2.5-VL-7B.
  arXiv  Detail & Related papers  (2025-05-28T15:11:16Z)
• 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)
• GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning [35.429904556288996]
  We introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification. Experimental results show that GenPRM significantly outperforms prior PRMs with only 23K training data from MATH dataset.
  arXiv  Detail & Related papers  (2025-04-01T15:21:05Z)
• 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)
• MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning [55.82649731348012]
  We introduce the MMK12 dataset and MM-EUREKA with 7B and 32B parameters.<n>The former is a high-quality multimodal mathematics reasoning dataset featuring diverse knowledge domains with human-verified answers and solution processes.<n>The latter is a multimodal model employing rule-based reinforcement learning utilizing online filtering and two-stage training strategy to enhance training stability.
  arXiv  Detail & Related papers  (2025-03-10T14:23:12Z)
• TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action [103.5952731807559]
  We present TACO, a family of multi-modal large action models designed to improve performance on complex, multi-step, and multi-modal tasks.<n>During inference, TACO produces chains-of-thought-and-action (CoTA), executes intermediate steps by invoking external tools such as OCR, depth estimation and calculator.<n>This dataset enables TACO to learn complex reasoning and action paths, surpassing existing models trained on instruction tuning data with only direct answers.
  arXiv  Detail & Related papers  (2024-12-07T00:42:04Z)
• 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)
• 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)
• Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement [71.46993852662021]
  We present a series of math-specific large language models: Qwen2.5-Math and Qwen2.5-Math-Instruct-1.5B/7B/72B. Qwen2.5-Math-Instruct supports both Chinese and English, and possess advanced mathematical reasoning capabilities.
  arXiv  Detail & Related papers  (2024-09-18T16:45:37Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning [13.728595670907136]
  We introduce InfinityMATH, a scalable instruction tuning dataset for programmatic mathematical reasoning. Fine-tuning experiments with open-source language and code models, such as Llama2 and CodeLlama, demonstrate the practical benefits of InfinityMATH.
  arXiv  Detail & Related papers  (2024-08-09T08:18:20Z)
• Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On [55.449818944278526]
  We introduce the Skywork-Math model series, supervised fine-tuned (SFT) on common 7B language models. Skywork-Math 7B has achieved impressive accuracies of 51.2% on the competition-level MATH benchmark. We provide several practical takeaways to enhance math reasoning abilities in LLMs for both research and industry applications.
  arXiv  Detail & Related papers  (2024-07-11T09:56:51Z)
• M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought [50.576016777061724]
  Multi-modal Chain-of-Thought (MCoT) requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning. The current MCoT benchmark still faces some challenges: (1) absence of visual modal reasoning, (2) single-step visual modal reasoning, and (3) Domain missing. We introduce a novel benchmark (M$3$CoT) to address the above challenges, advancing the multi-domain, multi-step, and multi-modal CoT.
  arXiv  Detail & Related papers  (2024-05-26T07:56:30Z)
• MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time [51.5039731721706]
  MindStar is a purely inference-based searching method for large language models. It formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths. It significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1.
  arXiv  Detail & Related papers  (2024-05-25T15:07:33Z)
• Markovian Transformers for Informative Language Modeling [0.9642500063568188]
  Chain-of-Thought (CoT) reasoning holds great promise for explaining language model outputs, but recent studies have highlighted significant challenges in its practical application for interpretability.<n>We make CoT causally essential to prediction through two key components: factoring next-token prediction through intermediate CoT text, and training CoT to predict future tokens independently of other context.
  arXiv  Detail & Related papers  (2024-04-29T17:36:58Z)
• DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models [21.85879890198875]
  Decentralized Iterative Merging-And-Training (DIMAT) is a novel decentralized deep learning algorithm. We show that DIMAT attains faster and higher initial gain in accuracy with independent and identically distributed (IID) and non-IID data, incurring lower communication overhead. This DIMAT paradigm presents a new opportunity for the future decentralized learning, enhancing its adaptability to real-world with sparse lightweight communication computation.
  arXiv  Detail & Related papers  (2024-04-11T18:34:29Z)
• Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning [110.80663974060624]
  Key-Point-Driven Data Synthesis (KPDDS) is a novel data synthesis framework that synthesizes question-answer pairs. KPDDS ensures the generation of novel questions with rigorous quality control and substantial scalability. We present KPMath, an extensive synthetic dataset tailored for mathematical reasoning, comprising over 800K question-answer pairs.
  arXiv  Detail & Related papers  (2024-03-04T18:58:30Z)
• How Do Humans Write Code? Large Models Do It the Same Way Too [14.954886191356342]
  Program-of-Thought (PoT) replaces natural language-based Chain-of-Thought (CoT) as the most popular method in Large Language Models. Using PoT introduces more reasoning errors, such as incorrect formulas or flawed logic, compared to CoT. We propose Human-Think Language (HTL), which leverages a suite of strategies that help integrate PoT and CoT.
  arXiv  Detail & Related papers  (2024-02-24T05:40:01Z)
• MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data [85.50740598523818]
  MUSTARD is a framework that masters uniform synthesis of theorem and proof data of high quality and diversity. We present a theorem-and-proof benchmark MUSTARDSAUCE with 5,866 valid data points. We perform extensive analysis and demonstrate that MUSTARD generates validated high-quality step-by-step data.
  arXiv  Detail & Related papers  (2024-02-14T05:57:58Z)
• MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline [12.186691561822256]
  We postulate that the inherent nature of large language models (LLMs) presents challenges in modeling mathematical reasoning. This paper introduces a novel math dataset, enhanced with a capability to utilize a Python code interpreter. We propose a tentative, easily replicable protocol for the fine-tuning of math-specific LLMs.
  arXiv  Detail & Related papers  (2024-01-16T08:08:01Z)
• Multimodal Chain-of-Thought Reasoning in Language Models [94.70184390935661]
  We propose Multimodal-CoT that incorporates language (text) and vision (images) modalities into a two-stage framework. Experimental results on ScienceQA and A-OKVQA benchmark datasets show the effectiveness of our proposed approach.
  arXiv  Detail & Related papers  (2023-02-02T07:51:19Z)

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.