用大模型根据自然语言目标自动生成规划领域的抽象表示。
Using Large Language Models for Abstraction of Planning Domains - Extended Version
- 基于自然语言指令，利用大模型生成抽象PDDL领域与问题实例。
- GPT-4o在简单场景下可生成有效抽象，对动作抽象优于对状态变量抽象。
- 适用于需要快速生成规划抽象的智能体设计与自动化系统开发。
在动态环境中，生成与特定目标一致的抽象表示仍是重大挑战，因为抽象选择直接影响智能体的规划、推理与解释能力。本文在PDDL中建模智能体的具体行为，研究使用大语言模型（LLMs）通过上下文学习生成抽象的PDDL领域与问题实例，输入为自然语言描述的抽象目标。所用基准示例为全新数据，未出现在任何大模型训练集中。考虑三类抽象：替代具体动作的选择抽象、具体动作序列的抽象、动作/谓词参数的抽象，以及其组合。生成的抽象通过符号验证工具与人工专家进行检验。实验表明，GPT-4o在简单设置下通常能生成有用的规划领域抽象，但对动作的抽象能力优于对相关非持久性状态（fluents）的抽象。
原文摘要 · Abstract (English)
Generating an abstraction of a dynamic domain that aligns with a given purpose remains a significant challenge given that the choice of such an abstraction can impact an agent's ability to plan, reason, and provide explanations effectively. We model the agent's concrete behaviors in PDDL and investigate the use of in-context learning with large language models (LLMs) for the generation of abstract PDDL domains and problem instances, given an abstraction objective specified in natural language. The benchmark examples we use are new and have not been part of the data any LLMs have been trained on. We consider three categories of abstractions: abstraction of choice of alternative concrete actions, abstraction of sequences of concrete actions, and abstraction of action/predicate parameters, as well as combinations of these. The generated abstract PDDL domains and problem instances are then checked by symbolic validation tools as well as human experts. Our experiments show that GPT-4o can generally synthesize useful planning domain abstractions in simple settings, although it is better at abstracting over actions than over the associated fluents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。