视觉思考，文本推理：抽象推理中的视觉-语言协同
Think Visually, Reason Textually: Vision-Language Synergy in Abstract Reasoning
论文揭示了视觉与语言在推理不同阶段的互补性：视觉擅长全局模式抽象与验证，语言擅长符号规则表述与精确执行。这为视觉研究者提供了一个可复用的思路——将视觉渲染作为验证模块嵌入文本推理流程，实现内在错误校正，尤其适用于需要从少量示例中归纳规则的少样本视觉推理任务。
原文依据 vision supports global pattern abstraction and verification, whereas language specializes in symbolic rule formulation and precise execution
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从少量示例中进行抽象推理仍然是 GPT-5 等前沿基础模型尚未解决的核心问题。这些模型仍然无法从少量示例中推断出结构化的变换规则，而这正是人类智能的一个关键标志。抽象与推理语料库（ARC-AGI）为这一能力提供了严格的测试平台，要求进行概念规则归纳并迁移到新任务。大多数现有方法将 ARC-AGI 视为纯文本推理任务，忽视了人类在解决此类谜题时严重依赖视觉抽象这一事实。然而，我们的实验揭示了一个悖论：将 ARC-AGI 网格简单地渲染为图像会因规则执行不精确而导致性能下降。这引出了我们的核心假设：视觉与语言在不同推理阶段具有互补优势：视觉支持全局模式抽象与验证，而语言则专长于符号规则表述与精确执行。基于这一洞见，我们引入了两种协同策略：（1）视觉-语言协同推理（VLSR），将 ARC-AGI 分解为模态对齐的子任务；（2）模态切换自校正（MSSC），利用视觉来验证基于文本的推理以实现内在错误校正。大量实验表明，我们的方法在多种旗舰模型和多个 ARC-AGI 任务上相比纯文本基线最高提升了 4.33%。我们的发现表明，将视觉抽象与语言推理统一起来是实现可泛化、类人智能的关键一步。
英文原文摘要 1659 字符
Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5. These models still fail to infer structured transformation rules from a handful of examples, which is a key hallmark of human intelligence. The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) provides a rigorous testbed for this capability, demanding conceptual rule induction and transfer to novel tasks. Most existing methods treat ARC-AGI as a purely textual reasoning task, overlooking the fact that humans rely heavily on visual abstraction when solving such puzzles. However, our experiments reveal a paradox: naively rendering ARC-AGI grids as images degrades performance due to imprecise rule execution. This leads to our central hypothesis that vision and language possess complementary strengths across distinct reasoning stages: vision supports global pattern abstraction and verification, whereas language specializes in symbolic rule formulation and precise execution. Building on this insight, we introduce two synergistic strategies: (1) Vision-Language Synergy Reasoning (VLSR), which decomposes ARC-AGI into modality-aligned subtasks; and (2) Modality-Switch Self-Correction (MSSC), which leverages vision to verify text-based reasoning for intrinsic error correction. Extensive experiments demonstrate that our approach yields up to a 4.33% improvement over text-only baselines across diverse flagship models and multiple ARC-AGI tasks. Our findings suggest that unifying visual abstraction with linguistic reasoning is a crucial step toward achieving generalizable, human-like intelligence.