CoT-TL：利用思维链推理实现规划指令的低资源时序知识表示
CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning
AI总结：
本文提出 CoT-TL 框架，通过思维链推理与语义角色在低资源条件下将自然语言规划指令转换为 LTL，并结合模型检查提升可靠性，在多数据集和无人机规划中验证其优越性能。
摘要：
自主智能体在执行规划任务时，常面临解释不确定自然语言指令的挑战。将这些指令表示为线性时序逻辑（LTL），可使规划器综合出可执行的计划。本文提出 CoT-TL，这是一种数据高效的上下文学习框架，用于将自然语言规约翻译为 LTL 表示。CoT-TL 通过扩展思维链推理和语义角色，使其与形式逻辑构建的要求保持一致，从而克服大型语言模型通常依赖大量微调数据的局限。该方法增强了 LTL 生成过程的透明度与推理依据，有助于建立用户信任。在低数据场景下，CoT-TL 在三个不同数据集上均达到最先进准确率，并且无需微调或中间翻译即可优于现有方法。为提高可靠性并最大限度减少幻觉，本文引入模型检查来验证所生成 LTL 输出的语法。本文还通过消融研究，以及在一个新数据集中对未见过的 LTL 结构和公式进行评估，进一步证明了 CoT-TL 的有效性。最后，本文将 CoT-TL 集成到四旋翼飞行器中，使其能够根据自然语言指令进行多步无人机规划，从而验证了该方法的实用性。项目详情：https://github.com/kumarmanas/TAMP_COT_TL
英文摘要：
Autonomous agents often face the challenge of interpreting uncertain natural language instructions for planning tasks. Representing these instructions as Linear Temporal Logic (LTL) enables planners to synthesize actionable plans. We introduce CoT-TL, a data-efficient in-context learning framework for translating natural language specifications into LTL representations. CoT-TL addresses the limitations of large language models, which typically rely on extensive fine-tuning data, by extending chain-of-thought reasoning and semantic roles to align with the requirements of formal logic creation. This approach enhances the transparency and rationale behind LTL generation, fostering user trust. CoT-TL achieves state-of-the-art accuracy across three diverse datasets in low-data scenarios, outperforming existing methods without fine-tuning or intermediate translations. To improve reliability and minimize hallucinations, we incorporate model checking to validate the syntax of the generated LTL output. We further demonstrate CoT-TL's effectiveness through ablation studies and evaluations on unseen LTL structures and formulas in a new dataset. Finally, we validate CoT-TL's practicality by integrating it into a QuadCopter for multi-step drone planning based on natural language instructions. Project details: \href{https://github.com/kumarmanas/TAMP\_COT\_TL}{https://github.com/kumarmanas/TAMP\_COT\_TL}
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
