The rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligence (AGI) due to their superior reasoning and generalization capabilities. Effective planning is crucial for the success of LLM agents in real-world tasks, making it a highly pursued topic in the community. Current planning methods typically translate tasks into executable action sequences. However, determining a feasible or optimal sequence for complex tasks at fine granularity, which often requires compositing long chains of heterogeneous actions, remains challenging. This paper introduces Meta-Task Planning (MTP), a zero-shot methodology for collaborative LLM-based multi-agent systems that simplifies complex task planning by decomposing it into a hierarchy of subordinate tasks, or meta-tasks. Each meta-task is then mapped into executable actions. MTP was assessed on two rigorous benchmarks, TravelPlanner and API-Bank. Notably, MTP achieved an average $\sim40\%$ success rate on TravelPlanner, significantly higher than the state-of-the-art (SOTA) baseline ($2.92\%$), and outperforming $LLM_{api}$-4 with ReAct on API-Bank by $\sim14\%$, showing the immense potential of integrating LLM with multi-agent systems.

翻译：神经语言模型的快速发展引发了智能体研究的新浪潮。与传统智能体不同，基于大语言模型的智能体（LLM 智能体）凭借其卓越的推理与泛化能力，已成为实现通用人工智能（AGI）的一种极具前景的范式。有效的规划对于 LLM 智能体在现实任务中取得成功至关重要，这使其成为该领域备受关注的研究方向。当前的规划方法通常将任务转化为可执行的动作序列。然而，对于需要组合长链异构动作的复杂任务，在细粒度上确定一个可行或最优的序列仍然具有挑战性。本文提出了元任务规划（MTP），这是一种面向基于 LLM 的协作式多智能体系统的零样本方法，它通过将复杂任务规划分解为一系列从属任务（即元任务）的层次结构来简化规划过程。每个元任务随后被映射为可执行的动作。我们在两个严格的基准测试（TravelPlanner 和 API-Bank）上评估了 MTP。值得注意的是，MTP 在 TravelPlanner 上取得了平均约 40% 的成功率，显著高于当前最先进（SOTA）基线的 2.92%，并在 API-Bank 上以约 14% 的优势超越了采用 ReAct 的 $LLM_{api}$-4，这展现了将 LLM 与多智能体系统相结合的巨大潜力。