cd /news/ai-safety/who-does-what-in-ai-auditing-designi… · home topics ai-safety article
[ARTICLE · art-137141] src=arxiv.org ↗ pub= topic=ai-safety verified=true sentiment=· neutral

Who Does What in AI Auditing? Designing Human-AI Collaboration for Auditing Generative AI

A September 21, 2026 arXiv paper introduces Human-Agent Audit Collaboration (HAAC), a workflow and system for structuring human-AI collaboration in AI auditing, evaluated with 71 auditors on conversational shopping agents. The study found AI assistance increased attack success and broadened exploration while also increasing auditors' reliance on AI-generated assessments and reports, and interviews with Responsible AI practitioners showed actionable audits require visibility into coverage, reproducible attack trajectories, and evaluation of the auditing agents themselves.

read2 min views1 publishedSep 22, 2026
Who Does What in AI Auditing? Designing Human-AI Collaboration for Auditing Generative AI
Image: source
  [Submitted on 21 Sep 2026]


[View PDF](http://arxiv.org/pdf/2609.24986v1)

[HTML (experimental)](https://arxiv.org/html/2609.24986v1)

Abstract:AI auditing increasingly incorporates AI agents to expand the scale and breadth of audit coverage, yet little is known about how auditing work should be divided without displacing human judgment. We introduce Human-Agent Audit Collaboration (HAAC), a workflow and system for structuring human-AI collaboration in AI auditing. Drawing on prior work and formative consultations with AI auditing practitioners, HAAC specifies how agents can support exploration, assessment, reporting, and review while preserving human oversight where contextual judgment is critical. We instantiate HAAC for conversational shopping agents and evaluate it through two studies. With 71 auditors, AI assistance increased attack success and broadened exploration, while also shaping later attacks and increasing auditors' reliance on AI-generated assessments and reports. Interviews with Responsible AI practitioners showed that actionable audits require visibility into coverage, reproducible attack trajectories, and evaluation of the auditing agents themselves. Our findings identify design considerations for effective and accountable human-AI auditing.

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?) alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?) Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?) arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

── more in #ai-safety 4 stories · sorted by recency
── more on @haac 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/who-does-what-in-ai-…] indexed:0 read:2min 2026-09-22 ·