arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.18082cs.CLcs.HC
收藏

Octo-planner:用于规划-行动智能体的设备端语言模型

Octo-planner: On-device Language Model for Planner-Action Agents

Nexa AI & Stanford(Nexa AI 与 斯坦福大学);MIT EECS(麻省理工学院电子工程与计算机科学系);MIT-IBM Watson AI Lab(麻省理工-IBM Watson AI 实验室)

Wei Chen, Zhiyuan Li, Zhen Guo, Yikang Shen

AI总结:

研究如何让人工智能智能体有效规划行动,提出设备端规划-行动框架,分离规划与行动执行组件,用模型微调优化性能,多LoRA训练方法应对多域规划挑战,在域内测试成功率达97%,并开源模型权重。

摘要:

人工智能智能体在各领域愈发重要,需有效规划过程。本文提出高效的设备端规划-行动框架,将规划与行动执行分离为两个组件:基于为边缘设备优化的38亿参数语言模型Phi-3 Mini的规划智能体,以及使用章鱼模型执行功能的行动智能体。规划智能体先将任务分解为子步骤响应用户查询,再由行动智能体执行。为在资源受限设备上优化性能,采用模型微调而非上下文学习。利用GPT-4生成规划查询和响应并验证数据质量,在精选数据集上微调Phi-3 Mini模型,在域内测试环境成功率达97%。还开发多LoRA训练方法应对多域规划挑战,开源了模型权重。

英文摘要:

AI agents have become increasingly significant in various domains, enabling autonomous decision-making and problem-solving. To function effectively, these agents require a planning process that determines the best course of action and then executes the planned actions. In this paper, we present an efficient on-device Planner-Action framework that separates planning and action execution into two distinct components: a planner agent based on Phi-3 Mini, a 3.8 billion parameter LLM optimized for edge devices, and an action agent using the Octopus model for function execution. The planner agent first responds to user queries by decomposing tasks into a sequence of sub-steps, which are then executed by the action agent. To optimize performance on resource-constrained devices, we employ model fine-tuning instead of in-context learning, reducing computational costs and energy consumption while improving response times. Our approach involves using GPT-4 to generate diverse planning queries and responses based on available functions, with subsequent validations to ensure data quality. We fine-tune the Phi-3 Mini model on this curated dataset, achieving a 97\% success rate in our in-domain test environment. To address multi-domain planning challenges, we developed a multi-LoRA training method that merges weights from LoRAs trained on distinct function subsets. This approach enables flexible handling of complex, multi-domain queries while maintaining computational efficiency on resource-constrained devices. To support further research, we have open-sourced our model weights at https://huggingface.co/NexaAIDev/octopus-planning. For the demo, please refer to https://www.nexa4ai.com/octo-planner.

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。

↑