---
title: "ComplianceAtlas: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.03121v1"
permalink: "https://feed.astralor.com/items/itm_3ec41352bb1bc44b2cd3eac1"
published: "2026-11-02T13:37:32.000Z"
score: 61
channel: "tech"
tags: ["AI Agent","安全","RAG","ComplianceAtlas","Taxonomy-Driven Agentic","Framework","Automated","Act Gap Analysis"]
---

# ComplianceAtlas: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation

## 速览

Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices. Compliance officers typ…

## 关键点

- Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices.
- Compliance officers typically admin- ister structured questionnaires collecting evi- dence of current practices, where organizations respond with descriptions of their existing pro- cesses, technical capabilities, and a…
- However, translating these compli- ance questionnaire responses into typed, ac- tionable gap diagnoses remains unsystematic.

## 全文

Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices. Compliance officers typically admin- ister structured questionnaires collecting evi- dence of current practices, where organizations respond with descriptions of their existing pro- cesses, technical capabilities, and architectural choices. However, translating these compli- ance questionnaire responses into typed, ac- tionable gap diagnoses remains unsystematic. In this paper, we present a literature-grounded taxonomy of technical compliance gaps cover- ing areas such as accuracy, robustness, logging, and human oversight, and embed it in GapTo- Compliance, a two-stage agentic framework coordinating two specialized agents: a Gap Extraction Agent that performs hierarchical rea- soning from compliance areas to specific gap types, and a Remediation Planning Agent that ranks remediation actions from a remediation catalog via multi-signal scoring combining se- mantic similarity, regulatory alignment, and effort estimation. We evaluate this framework against four automatic compliance gap detec- tion baselines across 9 AI systems and 6 AI families. Our approach achieves a gap-type F1 of 0.831 (vs. 0.533 for the strongest baseline) and remediation P@5 of 0.872 (vs. 0.635 for retrieval methods), demonstrating promising potential for automated compliance workflows. The structured agent coordination reveals a path toward human-in-the-loop compliance systems where automated gap extraction reduces expert burden while maintaining auditability, and the taxonomy-driven design enables extension to emerging regulatory frameworks beyond

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_3ec41352bb1bc44b2cd3eac1