用大模型实现自然语言到可执行计划的端到端转换
End-to-end PDDL Planning with Hardcoded and Dynamic Agents
- 通过可迭代修正的智能体将自然语言转化为PDDL模型
- 在多个经典难题上表现优于原生LLM，成功率超90%
- 适合需要自动化规划且不熟悉PDDL的开发者使用
我们提出一个由验证器支持的端到端规划框架。调度器接收自然语言形式的人类指令，转化为PDDL（规划领域定义语言）模型，并通过子模块（智能体）迭代优化领域与问题，以解决时间约束、最优性等常见需求，以及原始说明中的模糊与矛盾。智能体分为两类：硬编码型，基于日志和错误追踪预设目标（如修复语法、检查时序约束）；动态型，无预设目标，能自适应领域并改进潜在规划抽象。经验证的领域与问题被送入外部规划引擎生成计划。调度器与智能体均由大语言模型驱动，全程无需人工干预。最后，模块将最终计划翻译回自然语言，提升可读性同时保证步骤正确性。我们在GPT-{4o, 5-mini, 5.4}及Gemini-{2.5, 3}-flash上测试，覆盖十多个领域与任务，包括Google NaturalPlan基准、Planbench及Sokoban、Blocksworld、Hanoi Tower等经典问题。框架兼容任意PDDL规划引擎与验证器（已成功测试Fast Downward、LPG、POPF、VAL、uVAL），是大模型辅助端到端规划的重要进展。
原文摘要 · Abstract (English)
We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language and converts it into a PDDL (Planning Domain Definition Language) model, where the domain and problem are iteratively refined by sub-modules (agents) to address common planning requirements, such as time constraints and optimality, as well as ambiguities and contradictions that may exist in the human specification. We support two categories of agents: hardcoded, which are informed by logs and error traces and have a pre-defined goal (e.g., fix issues with PDDL syntax, check temporal constraints), and dynamic, which have no predefined goal but adapt to the specific domain and revise the latent planning abstraction. The validated domain and problem are then passed to an external planning engine to generate a plan. The orchestrator and agents are powered by Large Language Models (LLMs) and require no human intervention at any stage of the process. Finally, a module translates the final plan back into natural language to improve human readability while maintaining the correctness of each step. We demonstrate the flexibility and effectiveness of our framework on GPT-\{4o, 5-mini, 5.4\}, and Gemini-\{2.5, 3\}-flash across more than ten domains and tasks, including the Google NaturalPlan benchmark, Planbench, and classic planning problems like Sokoban, Blocksworld and the Tower of Hanoi, where LLMs are known to struggle even with small instances. Our framework can be integrated with any PDDL planning engine and validator (we successfully tested Fast Downward, LPG, POPF, VAL, and uVAL) and represents a significant step toward end-to-end planning aided by LLMs.
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。