Skip to content
Open access

From Model Explainability to Operational Transparency in Agentic AI: A Transparency-by-Design Framework for Critical Energy Systems Under the EU AI Act

Sep 2026 · Algorithms · 0 citations · 74 references

TL;DR

The transparency-by-design framework extends XAI from local model explanation to lifecycle-wide operational transparency for compliance-oriented development, without claiming legal conformity or field effectiveness.

Abstract

Agentic AI can coordinate distributed energy resources, invoke tools, revise plans, and act through multiple interacting agents. In critical energy systems, however, model-level explainable artificial intelligence (XAI) cannot reveal how goals, constraints, tools, delegations, authority, human intervention, and system changes combine to produce an operational action. This creates a regulatory and engineering gap wherever EU AI Act requirements for transparency, record-keeping, and human oversight apply. The transparency-by-design framework addresses this gap by treating operational transparency as a compositional property created through evidence continuity across model, agent, interaction, system, and lifecycle levels. It translates five regulatory transparency functions into eight components, a seven-stage gated lifecycle, stakeholder responsibilities, evidence artefacts, and acceptance criteria. Together, these elements specify what must be transparent, to whom, when, and how adequacy should be assessed and maintained. Regulatory analysis and thematic synthesis of 101 studies provide the evidence base. Application to an agentic virtual power plant demonstrates how forecasts, goals, plan revisions, inter-agent decisions, operator interventions, execution records, and system versions can be joined within one reconstructable evidence chain. The framework extends XAI from local model explanation to lifecycle-wide operational transparency for compliance-oriented development, without claiming legal conformity or field effectiveness.

Read PDF

Similar papers

AI-GRACE: A Use-Case Operationalization Framework for Agentic AI: From Organizational Objectives and Obligations to Deployment Capabilities and Architecture

This paper proposes AI-GRACE (Agentic Intelligence-Governance, Risk, Assurance, Controls, and Evidence) as a use-case operationalization framework connecting organizational governance with technical implementation, using design science to frame the method contribution and situational method engineering to guide context...

John Cuneo, David Chun, Gaurav Khanna · 1 citation
Open access Sep 2026

The transparency architecture in the AI Act: From system requirements to a right to explanation under article 86

The article provides a legal-dogmatic analysis of Article 86 AI Act and the newly introduced right to explanation, arguing that Article 86 constitutes an ex post and subsidiary practical safeguard aimed at mitigating information asymmetries in AI-assisted decision-making, rather than establishing a general right to alg...

Hajo Michael Holtz · 0 citations
#software testing Open access Oct 2026

From model trust to software topology: a Perspective on structurally governed agentic AI systems

This Perspective argues that agentic AI safety should move beyond exclusive reliance on model trust, alignment, or prompt-level defenses and should be treated as a software-architecture problem and developed a five-plane reference topology comprising intent, orchestration, execution, oversight, and adaptation.

Michai Morin, F. Sufi · 0 citations
#explainable ai Open access Sep 2026

From Explainability to Actionability: a Tiered Adaptable Multi-Agent Framework with Agent Reasoning Tools for Collaborative Failure Recovery

This research introduces a tiered multi-agent architecture grounded in Human-Centered eXplainable AI principles that contributes an adaptable and generalizable framework and foundational artifacts for trustworthy AI teammates.

Jie Tao, Li-Na Zhou · 0 citations
#artificial intelligence Review Sep 2026

From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments

Large language models become consequential agents when surrounding systems let outputs change external state. Models now call tools, operate interfaces, delegate work, retain state, inhabit generated worlds, and control robots or laboratory equipment. Such advances are often narrated as one march toward autonomy, confl...

Lin-Sen Zhu, Meng-Qing Cai · 2 citations

Agent-Integrated Software: Interaction Contracts and Continuous Assurance

This paper introduces Agent-Integrated Software (AIS) as a software pattern combining a conventional core, direct interaction, and a built-in agent, and Intent-Level Interaction Abstraction (IIA) as the task semantics through which users inspect and control delegated work.

Sheng-Cheng Yu, C. Fang, Zhen-Yu Chen · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.