---
id: 20260407-T0-15
title: "可微分符号规划：用于约束推理的神经架构"
title_en: "Differentiable Symbolic Planning for Constraint Reasoning"
url: https://ai.daily.yangsir.net/daily/20260407-T0-15
issue_date: 2026-04-07
publish_date: 2026-04-06T04:00:00.000Z
category: research
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2604.02350
---

# 可微分符号规划：用于约束推理的神经架构

arXiv论文提出Differentiable Symbolic Planning (DSP)，一种用于约束推理的神经架构。神经网络在模式识别方面表现出色，但在约束推理（判断配置是否满足逻辑或物理约束）方面存在困难。DSP通过结合符号规划与神经网络，实现了对约束可行性的可微分学习，为处理复杂约束问题提供了新方法，在规划、优化等领域有潜在应用价值。

## English Version

**Differentiable Symbolic Planning for Constraint Reasoning**

arXiv paper introduces Differentiable Symbolic Planning (DSP), a neural architecture for constraint reasoning. While neural networks excel at pattern recognition, they struggle with constraint reasoning—determining if configurations satisfy logical or physical constraints. DSP combines symbolic planning with neural networks to enable differentiable learning of constraint feasibility, offering new approaches for complex constraint problems.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2604.02350)

**详情页**：https://ai.daily.yangsir.net/daily/20260407-T0-15

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*