八达规划器：用于规划-动作代理的设备端语言模型

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

June 26, 2024

作者: Wei Chen, Zhiyuan Li, Zhen Guo, Yikang Shen

cs.AI

摘要

在各个领域中，AI代理变得越来越重要，实现了自主决策和问题解决。为了有效运行，这些代理需要一个规划过程，确定最佳行动方案，然后执行计划中的行动。本文介绍了一种高效的设备内规划-执行框架，将规划和行动执行分为两个独立组件：基于Phi-3 Mini的规划代理，这是一个针对边缘设备优化的38亿参数LLM，以及使用章鱼模型进行功能执行的行动代理。规划代理首先通过将任务分解为一系列子步骤来响应用户查询，然后由行动代理执行这些步骤。为了在资源受限设备上优化性能，我们采用模型微调而非上下文学习，降低计算成本和能耗，同时提高响应时间。我们的方法涉及使用GPT-4根据可用功能生成多样化的规划查询和响应，随后进行验证以确保数据质量。我们在这个筛选后的数据集上微调了Phi-3 Mini模型，在我们的领域内测试环境中实现了97%的成功率。为了解决多领域规划挑战，我们开发了一种多LoRA训练方法，将在不同功能子集上训练的LoRA的权重合并。这种方法在资源受限设备上实现了计算效率的同时，灵活处理复杂的多领域查询。为了支持进一步研究，我们已在https://huggingface.co/NexaAIDev/octopus-planning开源了我们的模型权重。有关演示，请参阅https://www.nexa4ai.com/octo-planner。

English

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.