Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

• URL: http://arxiv.org/abs/2509.06079v1
• Date: Sun, 07 Sep 2025 14:47:32 GMT
• Title: Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
• Abstract summary: We introduce a caption-assisted reasoning framework that effectively bridges visual and textual modalities.<n>Our approach achieved 1st place in the ICML 2025 AI for Math Workshop & Challenge 2: SeePhys, highlighting its effectiveness and robustness.
• Score: 13.14311042732615
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal scenarios. To address this gap, we introduce a caption-assisted reasoning framework that effectively bridges visual and textual modalities. Our approach achieved 1st place in the ICML 2025 AI for Math Workshop \& Challenge 2: SeePhys, highlighting its effectiveness and robustness. Furthermore, we validate its generalization on the MathVerse benchmark for geometric reasoning, demonstrating the versatility of our method. Our code is publicly available at https://github.com/OpenDCAI/SciReasoner.

Related papers

• From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning [12.586340785916066]
  We show that a pure Large Language Model (LLM) can rival state-of-the-art LMMs on complex geometry problems.<n>Our framework integrates a Symbolic Vision, which translates diagrams into symbolic form.<n>Our approach achieves performance comparable to Gemini 2.5 Pro while delivering clearer, human-like solutions.
  arXiv  Detail & Related papers  (2026-09-09T15:33:25Z)
• Vibe Reasoning: Eliciting Frontier AI Mathematical Capabilities -- A Case Study on IMO 2025 Problem 6 [28.84243696489176]
  We introduce Vibe Reasoning, a human-AI collaborative paradigm for solving complex mathematical problems.<n>We demonstrate this paradigm through IMO 2025 Problem 6, a optimization problem where autonomous AI systems publicly reported failures.
  arXiv  Detail & Related papers  (2025-12-22T11:30:19Z)
• Monet: Reasoning in Latent Visual Space Beyond Images and Language [55.424507246294326]
  "Thinking with images" has emerged as an effective paradigm for advancing visual reasoning.<n>Existing methods fall short of human-like abstract visual thinking.<n>We introduce Monet, a training framework that enables multimodal large language models to reason directly within the latent visual space.
  arXiv  Detail & Related papers  (2025-11-26T13:46:39Z)
• FormulaOne: Measuring the Depth of Algorithmic Reasoning Beyond Competitive Programming [19.576944188747166]
  FormulaOne is a benchmark for graph theory, logic, and algorithms.<n>Our problems are incredibly demanding, requiring an array of reasoning steps.<n>Remarkably, state-of-the-art models like OpenAI's o3 fail entirely on FormulaOne.
  arXiv  Detail & Related papers  (2025-07-17T17:53:55Z)
• Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving [48.22540519786074]
  Recent studies show that the informal accuracy exceeds 80% while formal success remains below 8% on benchmarks like PutnamBench.<n>We propose a novel framework that decouples high-level reasoning from low-level proof generation.<n>We evaluate our method on a challenging set of post-2000 IMO problems, a problem set on which no prior open-source prover has reported success.
  arXiv  Detail & Related papers  (2025-07-07T22:38:49Z)
• MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO [87.52631406241456]
  Recent text-to-image systems face limitations in handling multimodal inputs and complex reasoning tasks.<n>We introduce Mind Omni, a unified multimodal large language model that addresses these challenges by incorporating reasoning generation through reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-19T12:17:04Z)
• Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1) [66.51642638034822]
  Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks.<n>Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic domains.<n>This paper offers a concise yet insightful overview of reasoning techniques in both textual and multimodal LLMs.
  arXiv  Detail & Related papers  (2025-04-04T04:04:56Z)
• Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning [53.790502697674754]
  We propose Take-along Visual Conditioning (TVC), a strategy that shifts image input to critical reasoning stages.<n>TVC helps the model retain attention to the visual components throughout the reasoning.<n>Our approach achieves state-of-the-art performance on average across five mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-03-17T16:45:12Z)
• PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models [59.920971312822736]
  We introduce PromptCoT, a novel approach for automatically generating high-quality Olympiad-level math problems.<n>The proposed method synthesizes complex problems based on mathematical concepts and the rationale behind problem construction.<n>Our method is evaluated on standard benchmarks including GSM8K, MATH-500, and AIME2024, where it consistently outperforms existing problem generation methods.
  arXiv  Detail & Related papers  (2025-03-04T06:32:30Z)
• Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark [73.27104042215207]
  We introduce EMMA, a benchmark targeting organic multimodal reasoning across mathematics, physics, chemistry, and coding.<n>EMMA tasks demand advanced cross-modal reasoning that cannot be addressed by reasoning independently in each modality.<n>Our evaluation of state-of-the-art MLLMs on EMMA reveals significant limitations in handling complex multimodal and multi-step reasoning tasks.
  arXiv  Detail & Related papers  (2025-01-09T18:55:52Z)
• A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges [25.82535441866882]
  This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models (MLLMs)<n>We review over 200 studies published since 2021, and examine the state-of-the-art developments in Math-LLMs.<n>In particular, we explore multimodal mathematical reasoning pipeline, as well as the role of (M)LLMs and the associated methodologies.
  arXiv  Detail & Related papers  (2024-12-16T16:21:41Z)
• A Two-stage Fine-tuning Strategy for Generalizable Manipulation Skill of Embodied AI [15.480968464853769]
  We propose a novel two-stage fine-tuning strategy to enhance the generalization capability of our model based on the Maniskill2 benchmark. Our findings highlight the potential of our method to improve the generalization abilities of Embodied AI models and pave the way for their ractical applications in real-world scenarios.
  arXiv  Detail & Related papers  (2023-07-21T04:15:36Z)

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.