What Job Seekers Actually Want From AI Hiring: Explanations

Let’s Get You Hired: A Job Seeker’s Perspective on Multi-Agent Recruitment Systems for Explaining Hiring Decisions

Aditya Bhattacharya, Katrien Verbert · arXiv:2505.20312 (PDF) · submitted May 22, 2025

Summary by Andrew Johnson, OneTwo Resume editorial team · updated · We are not affiliated with the authors. arXiv papers are preprints and may not be peer-reviewed.

Nearly all recruitment AI is built for the employer. This KU Leuven study flips the perspective: a multi-agent LLM system designed to guide job seekers and explain hiring decisions, developed through user-centered design with active job seekers (a 4-person exploratory phase, then in-depth interviews with 20 more evaluating the prototype).

The consistent theme in what participants wanted: transparency. Candidates rarely get any justification for rejection, whether the decision came from a human or a black-box ATS — and the study demonstrates job seekers respond to systems that show their reasoning.

What the paper reports

What this means for your resume

Our editorial interpretation — the paper does not give job-seeker advice.

Read it with these caveats

arXiv preprint; small qualitative sample (24 job seekers total across phases) — rich on "what users want," not a quantitative evaluation of hiring outcomes.

Primary source: Let’s Get You Hired: A Job Seeker’s Perspective on Multi-Agent Recruitment Systems for Explaining Hiring Decisions — always read the paper before citing it. Spotted an error in our summary? Tell us and we'll fix it with a visible correction.

More in humans + ai deciding together