arXiv cs.AI· Yanchen Deng, Jianguo Huang, Yao Long Teng, Yixuan Li, Handuo Zhang, Ning Wang, Liangcai Su, Xinyu Wang, Bo An·· 2 天前AI 评分38
HTN-Orchestrate：面向多智能体编排的分层任务网络框架
HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration
AI 导读
HTN-Orchestrate 是一个两层多智能体编排框架，用分层任务网络分离全局规划与局部执行：Planner 维护子任务层级与依赖并推迟分解，Orchestrator 调度 worker 执行叶子子任务，结果按 AND 语义向上传播。
正文 · 原文
Abstract:Orchestrating multiple agents on a complex task requires reconciling local subtask execution with global task planning. Dynamic dispatch approaches provide execution flexibility but do not explicitly model subtask hierarchies or dependencies, while predefined workflows impose this structure but fix the decomposition before execution begins. Therefore, we introduce HTN-Orchestrate, a two-layer framework that separates these responsibilities through a hierarchical task network (HTN). The Planner maintains subtask hierarchies and dependencies, deferring decomposition until prerequisite results become available, while local Orchestrators schedule workers to execute each leaf subtask. Results propagate upward under \textbf{AND} semantics, and accumulated findings inform a rebuilt task network when the current decomposition cannot resolve the task. On five benchmarks spanning web research, scientific reasoning, and research workflows, HTN-Orchestrate outperforms ReAct, Agent Team, and DeepSeek Harness using the same base model, achieving 89.73% accuracy on BrowseComp and 73.44% on SUPERChem, exceeding Agent Team by 2.45 and 4.69 percentage points, respectively.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22195 [cs.AI] |
| (or arXiv:2610.22195v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22195 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yanchen Deng [view email]
[v1]
Thu, 15 Oct 2026 16:45:59 UTC (256 KB)
来源：arXiv cs.AI · arxiv.org