arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.08089cs.CLcs.AIcs.RO
收藏

面向行为树生成的大型语言模型训练与开发研究

A Study on Training and Developing Large Language Models for Behavior Tree Generation

Intelligent Game and Decision Lab (IGDL)(智能博弈与决策实验室);Tianjin Artificial Intelligence Innovation Center (TAIIC)(天津人工智能创新中心)

Fu Li, Xueying Wang, Bin Li, Yunlong Wu, Yanzhen Wang, Xiaodong Yi

AI总结:

本文提出基于大型语言模型的行为树生成框架,通过合成数据训练BTGen模型并引入多层次验证策略,以提升复杂任务中行为树自动生成的有效性与可执行性。

摘要:

本文对大型语言模型(LLM)在应对复杂任务自动生成行为树(BTs)这一具有挑战性的任务中的应用潜力进行了创新性探索。传统的人工行为树生成方法效率低下,并且高度依赖领域专业知识。另一方面,现有的自动行为树生成技术在任务复杂性、模型适应性和可靠性方面遇到瓶颈。为克服这些挑战,我们提出了一种利用LLM强大的表示和推理能力的新方法。本文的核心贡献在于设计了一个基于LLM的行为树生成框架,该框架涵盖了从数据合成、模型训练到应用开发和数据验证的完整流程。引入合成数据来训练行为树生成模型(BTGen模型),增强其对各种复杂任务的理解和适应性,从而显著提升其整体性能。为确保生成的行为树的有效性和可执行性,我们强调了数据验证的重要性,并引入了一种多层次验证策略。此外,我们探索了一系列以LLM为核心要素的智能体设计与开发方案。我们希望本文的工作能为对基于LLM的行为树生成感兴趣的研究人员提供参考。

英文摘要:

This paper presents an innovative exploration of the application potential of large language models (LLM) in addressing the challenging task of automatically generating behavior trees (BTs) for complex tasks. The conventional manual BT generation method is inefficient and heavily reliant on domain expertise. On the other hand, existing automatic BT generation technologies encounter bottlenecks related to task complexity, model adaptability, and reliability. In order to overcome these challenges, we propose a novel methodology that leverages the robust representation and reasoning abilities of LLMs. The core contribution of this paper lies in the design of a BT generation framework based on LLM, which encompasses the entire process, from data synthesis and model training to application developing and data verification. Synthetic data is introduced to train the BT generation model (BTGen model), enhancing its understanding and adaptability to various complex tasks, thereby significantly improving its overall performance. In order to ensure the effectiveness and executability of the generated BTs, we emphasize the importance of data verification and introduce a multilevel verification strategy. Additionally, we explore a range of agent design and development schemes with LLM as the central element. We hope that the work in this paper may provide a reference for the researchers who are interested in BT generation based on LLMs.

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。

↑