Htn-orchestrate improves multi-agent task coordination with flexible hierarchies
HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration
Artificial IntelligenceComputation and Language
Summary
Complex tasks often need many agents to work together, but it's hard to plan their jobs while letting them adapt during the work. The authors created HTN-Orchestrate, a system that keeps track of task steps in a flexible hierarchy. It waits for important information before deciding how to break down tasks and assigns small jobs to individual workers. This approach did better on several tests involving web research and science than some other similar AI methods.
What this means in practice
- •For software engineering teams: Design orchestrated multi-agent workflows that adapt task breakdowns based on intermediate results for complex software projects.
- •For data analysis teams: Coordinate multiple AI agents to split and manage research workflows dynamically for efficient data-driven investigations.
Authors
Yanchen Deng, Jianguo Huang, Yao Long Teng, Yixuan Li, Handuo Zhang, Ning Wang, Liangcai Su, Xinyu Wang, Bo An
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.