ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI
Agentic AI systems operating over geospatial data require more than autonomous reasoning and tool use; they must also support explicit orchestration, spatial validation, governance, provenance, failure handling, and human decision authority.
This paper introduces ANASSA, an agentic AI orchestration framework for spatial intelligence, and details its refinement from a high-level architectural (HLA) framework to a low-level architecture (LLA) through Design Science Research (DSR).
What happened
The paper presents the refinement of the ANASSA framework, originally introduced in arXiv:2609.14824, by applying Design Science Research (DSR) to translate high-level architectural responsibilities into a low-level architecture (LLA). This LLA includes 47 logical roles, versioned task graphs, and other components to support governed agentic execution over geospatial data.
Why it matters
The refinement of ANASSA into a low-level architecture is significant for AI developers and system architects as it provides a structured approach to implementing agentic AI systems that handle geospatial data with governance, validation, and human oversight, ensuring reliability and adaptability across different technologies and environments.
- ANASSA's refinement into LLA ensures structured implementation of agentic AI systems for geospatial data.
- The design emphasizes governance, validation, and human oversight, critical for reliable AI systems.
- The architecture is technology-agnostic, allowing flexibility across different platforms and environments.
The bigger picture
The ANASSA LLA design enables more robust and adaptable agentic AI systems for geospatial applications, facilitating better governance, traceability, and testability. It allows for implementation without being tied to specific AI models or platforms, promoting flexibility and future-proofing.
The paper successfully refines the ANASSA framework into a low-level architecture, providing a comprehensive and adaptable design for agentic AI systems that operate on geospatial data, with a focus on governance, traceability, and testability.
Technical details
- High-Level Architecture (HLA) responsibilities
- Low-Level Architecture (LLA)
- Design Science Research (DSR)
- 47 logical roles
- Versioned task graphs
- Capability-based agent selection
- Typed contracts
- Explicit runtime states
- Spatial validation mechanisms
- Governance controls
FAQ
What is ANASSA?
ANASSA is an agentic AI orchestration framework for spatial intelligence that establishes high-level components and responsibility boundaries for governed agentic execution.
What does the paper contribute?
The paper contributes a refinement of ANASSA from a high-level architectural (HLA) framework to a low-level architecture (LLA) using Design Science Research (DSR), including 47 logical roles, versioned task graphs, and spatial validation mechanisms.
Why is the low-level architecture important?
The low-level architecture provides a structured implementation bridge for ANASSA, enabling inspectable, reconstructable, and testable workflows without binding to specific AI models, geospatial platforms, or deployment environments.
This summary and analysis were generated with AI from the original article and may contain errors. Read the original for the full story.
Read the full story
Originally published by arXiv - cs.AI on Oct 14, 2026.
Comments
Sign in to join the discussion.