AI 中文总结
该研究针对示例编程提出感知求解器分解框架，通过结合监督训练与冻结合成器的直接反馈优化分解器，突破GT分解的局限，在两个PBE领域提升了合成与任务准确性。
AI 中文摘要
基于分解的示例编程（PBE）通过将任务拆分为学习型合成器可解决的子任务来提升性能：分解器预测中间子目标，合成器则基于这些子目标生成程序。现有方法训练分解器以模仿真实值（GT）子目标，隐含地将分解质量视为任务的固有属性。我们对这一假设提出质疑：对于具有固定归纳偏置的有界求解器而言，GT分解反映的是标注者的分解选择，而非求解器的搜索动态。因此，训练以匹配GT分解的分解器可能会提出逻辑上有效但求解器难以处理的子目标。我们提出感知求解器分解（SAD），这一训练框架保留了对GT子目标的监督训练作为结构支架，同时还通过来自冻结合成器的直接反馈来优化分解器。子目标的奖励基于合成器在目标程序上的损失，这是一种子任务难度的信号，鼓励生成求解器可处理的分解。我们的实验揭示了一个准确性悖论：与GT分解的更高一致性并不会提升合成成功率——即便合成器是在分解器被优化以模仿的相同GT数据上训练的。相反，SAD学习到的分解在GT对齐与求解器可处理性之间进行权衡，在两个PBE领域均实现了合成及端到端任务准确性的持续提升。此外，SAD还能解决GT分解神谕无法处理的任务——这一实证证据表明，GT分解并非有界求解器的通用最优解，且分解质量是与求解器相关的，而非固有属性。
英文摘要
Decomposition-based Programming-by-example (PBE) scales performance by splitting tasks into subtasks that a learned synthesizer solves: a decomposer predicts intermediate subgoals, and a synthesizer generates programs conditioned on them. Execution-decomposition approaches such as ExeDec train the decomposer to imitate ground-truth (GT) subgoals, implicitly treating decomposition quality as intrinsic to the task. We challenge this assumption: for bounded solvers with fixed inductive biases, GT decompositions reflect the annotator's factorization choices - not the solver's search dynamics. A decomposer trained to match GT decompositions may therefore propose subgoals that are logically valid yet intractable for the solver. We propose Solver-Aware Decomposition (SAD), a training framework that retains supervised training on GT subgoals as a structural scaffold, while additionally optimizing the decomposer online with policy gradients against a frozen learned synthesizer. Each sampled subgoal is rewarded by the synthesizer's cross-entropy loss on the target program - a continuous signal of subtask difficulty that encourages decompositions the solver can act on. Our experiments reveal an accuracy paradox: higher agreement with GT decompositions does not improve synthesis success - even though the synthesizer was trained on the very same GT data the decomposer is optimized to mimic. SAD instead learns decompositions that trade GT alignment for solver tractability, yielding consistent gains in synthesis and end-to-end task accuracy across two PBE domains and under zero-shot transfer to an external list-processing benchmark. Moreover, SAD solves tasks that a GT decomposition oracle fails - empirical evidence, under an identical synthesizer and search procedure, that GT decompositions are not universally optimal for bounded solvers.
CommentsAccepted at NeurIPS 2026
