Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism

TL;DR

This paper introduces a hierarchical task abstraction mechanism for designing domain-specific multi-agent systems, demonstrated through EarthAgent for geospatial analysis, improving planning accuracy over existing methods.

Contribution

The paper proposes a novel hierarchical task-centric framework for multi-agent systems, tailored for specialized domains, and demonstrates its effectiveness with EarthAgent and GeoPlan-bench.

Findings

EarthAgent outperforms existing multi-agent systems in geospatial tasks.

The hierarchical architecture enforces procedural correctness and task decomposition.

GeoPlan-bench provides a comprehensive evaluation platform for complex geospatial planning.

Abstract

LLM-driven agents, particularly those using general frameworks like ReAct or human-inspired role-playing, often struggle in specialized domains that necessitate rigorously structured workflows. Fields such as remote sensing, requiring specialized tools (e.g., correction, spectral indices calculation), and multi-step procedures (e.g., numerous intermediate products and optional steps), significantly challenge generalized approaches. To address this gap, we introduce a novel agent design framework centered on a Hierarchical Task Abstraction Mechanism (HTAM). Specifically, HTAM moves beyond emulating social roles, instead structuring multi-agent systems into a logical hierarchy that mirrors the intrinsic task-dependency graph of a given domain. This task-centric architecture thus enforces procedural correctness and decomposes complex problems into sequential layers, where each layer's sub-agents operate on the outputs of the preceding layers. We instantiate this framework as EarthAgent, a multi-agent system tailored for complex geospatial analysis. To evaluate such complex planning capabilities, we build GeoPlan-bench, a comprehensive benchmark of realistic, multi-step geospatial planning tasks. It is accompanied by a suite of carefully designed metrics to evaluate tool selection, path similarity, and logical completeness. Experiments show that EarthAgent substantially outperforms a range of established single- and multi-agent systems. Our work demonstrates that aligning agent architecture with a domain's intrinsic task structure is a critical step toward building robust and reliable specialized autonomous systems.