Current artificial intelligence systems, despite remarkable capabilities in text generation and pattern recognition, exhibit a fundamental architectural limitation: they resolve ambiguity prematurely. This premature semantic collapse -- the tendency to collapse multiple valid interpretations into a single output -- stems from classical identity assumptions embedded in standard neural architectures. We propose Non-Resolution Reasoning (NRR), a computational framework that treats ambiguity retention as a valid reasoning mode rather than a defect to be eliminated. NRR introduces three core principles: (1) Non-Identity (A $\ne$ A) -- the same symbol refers to different entities across contexts; (2) Approximate Identity (A $\approx$ A) -- entities share partial structural overlap without being identical; and (3) Non-Resolution -- conflicting interpretations can coexist without forced convergence. We formalize these principles through three architectural components: Multi-Vector Embeddings for context-dependent representation, Non-Collapsing Attention for parallel interpretation retention, and Contextual Identity Tracking (CIT) for maintaining A $\ne$ A across inference. We demonstrate NRR's advantages through case studies in paradox handling, creative generation, and context-dependent reasoning. Crucially, we provide a minimal empirical validation on a synthetic context-shift task where an NRR-lite model achieves 90.9% out-of-distribution accuracy compared to 9.1% for standard architectures, demonstrating that ambiguity preservation enables structural generalization. NRR challenges the assumption that meaning must collapse to be useful, offering a foundation for AI systems capable of sophisticated ambiguity handling and creative reasoning. The question is not whether AI should resolve ambiguity, but when, how, and under whose control.

翻译：当前的人工智能系统虽然在文本生成与模式识别方面展现出卓越能力，却存在一个根本性的架构局限：它们过早地消解了歧义。这种过早的语义坍缩——即将多种有效解释强制收敛为单一输出的倾向——源于标准神经架构中嵌入的经典身份假设。我们提出非消解推理（NRR），一种将歧义保留视为有效推理模式而非待消除缺陷的计算框架。NRR 提出三个核心原则：（1）非同一性（A $\\ne$ A）——同一符号在不同上下文中指代不同实体；（2）近似同一性（A $\\approx$ A）——实体间存在部分结构重叠而非完全等同；（3）非消解性——相互冲突的解释可在无需强制收敛的情况下共存。我们通过三个架构组件对这些原则进行形式化：用于上下文依赖表示的多向量嵌入、用于并行解释保留的非坍缩注意力机制，以及用于在推理过程中维持 A $\\ne$ A 的上下文身份追踪（CIT）模块。我们通过悖论处理、创造性生成和上下文依赖推理的案例研究展示了 NRR 的优势。关键的是，我们在一个合成上下文迁移任务上进行了最小化实证验证：NRR 简化模型取得了 90.9% 的分布外准确率，而标准架构仅为 9.1%，证明歧义保留能够实现结构泛化。NRR 挑战了“意义必须坍缩才有效用”的假设，为能够处理复杂歧义并进行创造性推理的 AI 系统奠定了基础。问题不在于 AI 是否应消解歧义，而在于何时消解、如何消解以及由谁控制消解过程。