通过全局规划与分层执行，提升大模型智能体的任务完成率。
Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution
- 引入持续更新的全局规划机制，避免局部困局。
- 分层执行策略使任务成功率提升12.22%。
- 适合需要多工具协作的复杂真实任务场景。
基于大语言模型（LLMs）的智能体系统在现实应用中展现出巨大潜力，但现有框架在任务规划与执行方面仍存在关键局限，制约其有效性与泛化能力。当前规划方法常缺乏清晰全局目标，导致智能体陷入局部分支或生成不可执行计划；而执行机制难以平衡复杂性与稳定性，且动作空间有限，难以应对多样化现实任务。为此，我们提出GoalAct框架，引入持续更新的全局规划机制，并整合分层执行策略。GoalAct将任务执行分解为搜索、编程、写作等高层技能，降低规划复杂度，增强跨场景适应性。我们在LegalAgentBench上进行评估，该基准包含多种需使用多种工具的法律任务。实验结果表明，GoalAct实现领先性能，平均成功率提升12.22%。这些发现凸显其推动更先进智能体系统发展的潜力，使其在复杂现实应用中更具实效。代码已开源：https://github.com/cjj826/GoalAct。
原文摘要 · Abstract (English)
Intelligent agent systems based on Large Language Models (LLMs) have shown great potential in real-world applications. However, existing agent frameworks still face critical limitations in task planning and execution, restricting their effectiveness and generalizability. Specifically, current planning methods often lack clear global goals, leading agents to get stuck in local branches, or produce non-executable plans. Meanwhile, existing execution mechanisms struggle to balance complexity and stability, and their limited action space restricts their ability to handle diverse real-world tasks. To address these limitations, we propose GoalAct, a novel agent framework that introduces a continuously updated global planning mechanism and integrates a hierarchical execution strategy. GoalAct decomposes task execution into high-level skills, including searching, coding, writing and more, thereby reducing planning complexity while enhancing the agents' adaptability across diverse task scenarios. We evaluate GoalAct on LegalAgentBench, a benchmark with multiple types of legal tasks that require the use of multiple types of tools. Experimental results demonstrate that GoalAct achieves state-of-the-art (SOTA) performance, with an average improvement of 12.22% in success rate. These findings highlight GoalAct's potential to drive the development of more advanced intelligent agent systems, making them more effective across complex real-world applications. Our code can be found at https://github.com/cjj826/GoalAct.
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。