Agentic Generation and Evolution of Knowledge Models

2026-06-02

AI Summary

This work addresses the challenge that continuous evolution of complex software systems often leads to knowledge models that are incomplete, inconsistent, or outdated, thereby undermining trustworthy reasoning and maintenance. To tackle this issue, the paper proposes TrustModel, a novel framework that introduces, for the first time, a multi-agent collaborative mechanism comprising three specialized agent subsystems—modeling, consistency verification, and evolution—to enable automated generation and dynamic synchronization of knowledge models. This approach yields a self-sustaining “living” knowledge model ecosystem. Integrating agent-based architecture with Model-Driven Engineering (MDE) techniques, TrustModel has been empirically validated in model-driven testing and demonstrates broad applicability across tasks such as requirement monitoring, architectural drift tracking, and change impact analysis.

Abstract

Complex software systems such as autonomous vehicles, robotics increasingly interact with dynamic physical, cyber, and social environments. Reasoning about their behavior, maintaining them under continuous change, and evolving them safely require trustworthy knowledge about the system, its assumptions, and its operating context. Knowledge models (KMs) provide a practical basis for such reasoning, but they may themselves become incomplete, inconsistent, or outdated as systems evolve. This paper presents TrustModel, a vision for the agentic generation and evolution of living KMs. TrustModel comprises three agentic subsystems: Modeling, for constructing and updating KMs; Conformance, for assessing their alignment with the system and its environment; and Evolution, for generating guidance to keep KMs synchronized with emerging changes. We demonstrate how TrustModel can be instantiated for model-based testing and discuss its potential for supporting other MDE activities, such as requirements and assumption monitoring, architectural drift tracking, and change impact assessment. Overall, TrustModel positions living KMs as a foundation for dependable engineering of continuously evolving software systems.

Problem

• Knowledge Models
• Software Evolution
• Trustworthiness
• Dynamic Environments
• Model Inconsistency

Innovation

• Agentic Knowledge Models
• TrustModel
• Model Evolution
• Conformance Checking
• Living Knowledge Models