将任务分解为图结构，实现大模型并行规划，提升执行效率。
Plan-over-Graph: Towards Parallelable LLM Agent Schedule
- 把任务转为抽象图，让模型理解后生成可并行的计划。
- 在多个模型上测试，性能显著优于传统串行规划方法。
- 适合需要高效多步骤执行的自动化系统开发人员使用。
大型语言模型在任务规划推理方面表现出色，但在并行调度方面的挑战仍待解决。本文提出一种新范式——‘计划-图’（plan-over-graph），即模型先将真实文本任务分解为可执行子任务，并构建抽象任务图；随后以该图为输入，生成支持并行执行的计划。为提升复杂、可扩展图的规划能力，我们设计了自动可控的合成图生成管道，并提出两阶段训练方案。实验表明，该方法在基于API的LLM及可训练开源模型上均显著提升任务表现。通过将复杂任务标准化为图结构，该方法天然支持并行执行，展现出全局效率优势。代码与数据已公开于 https://github.com/zsq259/Plan-over-Graph。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph. The model then understands this task graph as input and generates a plan for parallel execution. To enhance the planning capability of complex, scalable graphs, we design an automated and controllable pipeline to generate synthetic graphs and propose a two-stage training scheme. Experimental results show that our plan-over-graph method significantly improves task performance on both API-based LLMs and trainable open-sourced LLMs. By normalizing complex tasks as graphs, our method naturally supports parallel execution, demonstrating global efficiency. The code and data are available at https://github.com/zsq259/Plan-over-Graph.
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。