用大模型生成可验证的规划器，提升智能体的可靠性与效率
Planning in the LLM Era: Building for Reliability and Efficiency
- 让大模型在构造阶段生成符号化规划算法
- 生成的规划器可验证且推理时无需依赖大模型
- 适合追求高效可靠智能体的研究者
智能体的发展使规划能力备受关注。早期利用大语言模型（LLMs）进行规划的方法多采用单次生成，后续发展为结合有限外部搜索的混合方法，但这些方法因本质不严谨且不完整，常需大量资源却无法解决新问题。随着对大模型局限性的认知加深，近期研究转向在求解构造阶段使用大模型：生成可验证的符号规划器，推理时高效调用。这一趋势体现了对可靠、高效智能体的需求，也为构建低依赖大模型的可维护规划器提供了路径。本文分析了三类规划器生成方法，讨论其当前局限，并提出迈向更可靠高效的基于大模型规划器生成的研究方向。
原文摘要 · Abstract (English)
Growing attention to intelligent agents has put a spotlight on one of their central capabilities: planning. Early attempts to leverage large language models (LLMs) for planning relied on single-shot plan generation, followed by hybrid approaches that coupled LLMs with limited external search. These methods, unsound and incomplete by their very nature, often require substantial resources without yielding better solutions on unseen problems. As the limitations of LLMs become clearer, recent work has shifted toward using them at solution construction time -- generating symbolic solvers for a family of problems that can be verified and then used efficiently at inference time. This trend reflects the growing need for agents that are both reliable and resource-efficient. It also offers a path towards generating maintainable planners with minimal dependence on language models at inference time. In this paper, we argue that this shift reflects a broader realignment of the planning field in the LLM era. We examine three major categories of planner-generation methods, discuss their current limitations, and outline research steps towards a more reliable and efficient LLM-based generation of planners.
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。