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
- A multi-agent LLM recruitment prototype built around explaining decisions to candidates.
- Design grounded in a two-phase study with active job seekers; evaluated via qualitative interviews with 20 participants.
- Documents the transparency gap in both human and ATS-driven rejection as the motivating problem.
What this means for your resume
Our editorial interpretation — the paper does not give job-seeker advice.
- The research community is on record that you deserve explanations — worth remembering when a rejection arrives with none. Regulatory pressure (NYC’s AEDT law, the EU AI Act’s high-risk classification for hiring) is slowly pushing the same direction.
- Until then, the practical substitute for an explanation is instrumentation: track which resume version went where, and treat response-rate differences as your own experiment.
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.