发表机构
IBM; DeepMind（IBM公司; 深度思维公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该论文指出将概率范式用于量子电路合成有误，因量子电路有语法语义差距，未经验证的训练使模型难掌握物理语义，有效子集随量子比特数指数衰减。提出转向以验证器为中心，集成多种元素到生成中，验证意识架构是可行途径，应编码特定规则而非仅靠模仿。
AI 中文摘要
缩放假设认为增加模型参数会产生新兴推理能力。本文认为将这种概率范式应用于通用量子电路合成是一个方向性错误。与自然语言不同，量子电路需要严格遵守数学约束，这导致了显著的语法-语义差距。对未经验证的量子程序进行训练意味着模型学习语法但无法捕捉希尔伯特空间的物理语义。由于电路设计的有效子集随量子比特数量呈指数衰减，事后过滤在数学上是难以处理的。我们提出从以人类为中心的副驾驶转向以验证器为中心的代理。我们将分层约束、拓扑掩码和符号代理直接集成到生成过程中。我们的分析表明，仅靠规模无法弥合有效性差距。具有验证意识的架构为模块化量子程序生成提供了一条可行的途径。这些考虑指向了编码量子信息特定任务规则的生成方法，而不是仅仅依赖模仿。
英文摘要
The scaling hypothesis assumes that increasing model parameters yields emergent reasoning capabilities. This position paper argues that applying this probabilistic paradigm to generic quantum circuit synthesis is a directional error. Unlike natural languages, quantum circuits require strict adherence to mathematical constraints that manifest a significant syntax-semantics gap. Training on unverified quantum programs means that models learn syntax but fail to capture the physical semantics of the Hilbert space. Since the valid subset of circuit designs decays exponentially with the number of qubits, post-hoc filtering is mathematically intractable. We propose a pivot from human-centric copilots to verifier-centric agents. We integrate hierarchical constraints, topological masks, and symbolic proxies directly into generation. Our analysis suggests that scale alone cannot bridge the validity gap. Verification-aware architectures offer a viable path for modular quantum program generation. These considerations point toward generation methods that encode task-specific rules of quantum information, rather than relying on imitation alone.
CommentsAccepted to ICML 2026: https://openreview.net/forum?id=oX1vWuQ13y
