用大模型逐步构建可规划的环境模型，解决信息不全时的智能决策问题。
Iterative Formalization and Planning in Partially Observable Environments
- 通过分解环境与目标为可观察片段，迭代生成并优化PDDL描述
- 无需微调或示例，在复杂任务中成功率显著优于端到端方法
- 成功经验可积累用于后续任务，适合需要持续学习的场景
以往方法多依赖大模型直接预测计划，而本文提出PDDLego框架，利用大模型将部分可观测环境逐步形式化为规划领域定义语言（PDDL）表示。不同于仅适用于完全可观测环境的方法，该框架通过将环境和目标分解为一系列可观察的子阶段，实现迭代式形式化、规划、扩展与精炼。该方法无需微调、上下文示例或轨迹数据，在面对复杂问题时表现出更强的鲁棒性与更高的规划成功率。此外，单次成功后积累的领域知识可被用于后续任务，提升整体效率。
原文摘要 · Abstract (English)
Using LLMs not to predict plans but to formalize an environment into the Planning Domain Definition Language (PDDL) has been shown to improve performance and control. While most existing methodology only applies to fully observable environments, we adapt to the more realistic and challenging partially observable environments without sufficient information to make a complete plan. We propose PDDLego, a framework to iteratively formalize, plan, grow, and refine PDDL representations by decomposing the environment and the goal into fully observable episodes. Without finetuning, in-context exemplars, or trajectories, PDDLego improves planning success and exhibits robustness against problem complexity compared to end-to-end approaches. We also show that the domain knowledge captured after a successful trial can benefit future tasks.
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。