---
id: 20261025-T0-04
title: "MemPlan：让LLM当语言与符号规划之间的翻译层"
title_en: "MemPlan Uses LLMs as Bridges Between Language and Symbolic Planning"
url: https://ai.daily.yangsir.net/daily/20261025-T0-04
issue_date: 2026-10-25
publish_date: 2026-10-24T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2610.30379
---

# MemPlan：让LLM当语言与符号规划之间的翻译层

arXiv新论文MemPlan提出一种记忆条件化的PDDL规划方法，面向部分可观测的文本环境。研究不再把LLM当作长程规划器，因为那样成本高且容易产生幻觉或无效动作，而是让LLM充当自然语言与符号规划之间的受限桥梁，由符号规划器负责决策，并用记忆机制处理部分可观测信息。这种方法试图兼顾LLM的语言理解能力和经典规划的可靠性，适用于需要在不确定信息下执行多步任务的智能体。

## English Version

**MemPlan Uses LLMs as Bridges Between Language and Symbolic Planning**

A new arXiv paper, MemPlan, proposes memory-conditioned PDDL planning for partially observable text environments. Rather than using LLMs as long-horizon planners, which is costly and prone to hallucinated or invalid actions, the work positions LLMs as constrained bridges between natural language and symbolic planning, letting a symbolic planner make decisions while a memory mechanism handles partial observability. The approach aims to combine LLM language understanding with the reliability of classical planning, targeting agents that must execute multi-step tasks under uncertain information.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2610.30379)

**详情页**：https://ai.daily.yangsir.net/daily/20261025-T0-04

---

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