Skip to content

Func-R1: Incentivizing Mathematical Function Reasoning in Multimodal Large Language Models

Sep 2026 · Conference on Empirical Methods in Natural Language Processing · Vol abs/2609.14779, pp. 40616-40632 · 1 citation · 34 references
Computer Science

TL;DR

Func-R1 is proposed, which synergistically harmonizes precise visual perception and rigorous logical reasoning and delivers the optimal performance among open-source MLLMs, even surpassing GPT-5 with an 8.4% improvement on MathVerse's function-oriented tasks.

Abstract

Performing deliberate mathematical reasoning in visual contexts is a hallmark of advanced Multimodal Large Language Models (MLLMs) and requires a sophisticated synthesis of perceptual grounding and symbolic logic. However, in the realm of mathematical functions, our investigation reveals a critical modality interference phenomenon: even advanced models, while performing textual computational reasoning, tend to disregard or misinterpret essential visual cues. To address this challenge, we propose Func-R1, which synergistically harmonizes precise visual perception and rigorous logical reasoning. Concretely, built upon an explicitly decoupled architecture, we employ a hierarchical post-training framework to progressively identify critical visual evidence and conduct in-depth theoretical reasoning. Furthermore, the Perception-Aligned Theoretic Optimization (PATO) strategy is proposed to steer policy updating towards internalizing fundamental theoretical properties while dynamically rectifying heterogeneous visual information throughout the reasoning process. Extensive experiments across diverse benchmarks demonstrate that Func-R1 delivers the optimal performance among open-source MLLMs, even surpassing GPT-5 with an 8.4% improvement on MathVerse's function-oriented tasks.

Read PDF

Similar papers

#artificial intelligence Preprint Oct 2026

Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning

The introduction of long chain-of-thought (CoT) reasoning and external tools has substantially improved the performance of multimodal large language models (MLLMs) on general and reasoning tasks. However, existing fast-slow reasoning paradigms mainly regulate textual reasoning length, while visual computation introduce...

Quan-Lin Chen, Xiu-Wei Chen, Kun Xiang et al. · 0 citations
Book Open access Nov 2026

Beyond Answer Accuracy: Diagnosing Perception Failures in Multimodal Mathematical Reasoning

Multimodal Large Language Models (MLLMs) have shown strong performance on mathematical reasoning tasks that combine textual and visual information. However, final-answer accuracy offers limited insight into whether errors arise from incorrect perception, modality-dependent information extraction, or downstream reasonin...

Aniket Mitra, Arpit Chhabra, Aditya Desai et al. · 0 citations
Conference Open access Oct 2026

Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning

Recent multimodal large language models achieve promising results on visual reasoning tasks, approaching human-level performance on existing STEM benchmarks. However, these capabilities degrade under complex real-world scenes. We identify that chain-of-thought reasoning remains largely confined to the linguistic space,...

Fan Yang, Li-Feng Chen, Yi-Pu Wang et al. · 0 citations

MM-OPD: Towards One More Bottleneck Between Perception and Reasoning

MM-OPD is introduced, a multimodal on-policy self-distillation framework for symbolic-to-visual correction that transfers guidance from symbolic-conditioned behavior to the image-conditioned policy through residual token-level targets, steering the model toward correct visual evidence.

Jin-Tao Tong, Yujing Lou, Zhan-Ming Shen et al. · 0 citations
Sep 2026

DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning

This work proposes Dense Reasoning Trace, a paradigm that departs from natural-language-centered CoT by expressing reasoning as compact structured traces, which include concise intermediate states with symbolic connectors and disentangle visual observations from logical deductions, and proposes the Trace-Grounded Reinf...

Wan Xu, Yuan-Fan Guo, Kevin Han et al. · 0 citations
Preprint Oct 2026

Think, Compress, Answer: Reinforcement Learning for Multimodal Grounding via Reasoning Compression

Extended reasoning has substantially improved multimodal large language models (MLLMs) on tasks requiring compositional and relational inference. However, multimodal grounding imposes a distinct requirement: reasoning must ultimately converge on a target-specific compact representation that supports precise localizatio...

J. Seo, Hyeongjun Kwon, Jiyoung Lee et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.