Two-agent systems change who passes resume screening and how often
When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening
Artificial IntelligenceComputation and Language
Summary
Hiring usually starts with a quick yes-or-no decision about a résumé based on a match with a job. The authors studied a smarter way where two AI agents—one representing the employer and one representing the candidate—can talk to each other, share info, and rethink their decisions. This two-agent method lets more candidates pass, but it also changes which candidates get through compared to the usual single-check approach. Interestingly, the candidates selected only by the two-agent system are less likely to be chosen again consistently, meaning this method can make screening less predictable.
What this means in practice
- •For recruitment software developers: Design automated screening that models employer and candidate viewpoints interacting to improve selection diversity and responsive decisions.
- •For human resources teams: Implement nuanced screening to identify candidates who may benefit from deeper review beyond static résumé-job matching.
Authors
Jian Gao, Hang Jiang
Abstract
Hiring is bilateral: employers assess fit, while candidates present and defend evidence of their qualifications. Yet résumé screening, the first gate, is commonly automated as a static, one-call judgment over a résumé-job pair. We study a two-agent alternative in which employer-side and candidate-side agents represent these roles, exchange evidence, and update their judgments before deciding who advances. We compare procedures on 600 constructed résumé-job pairs using GPT-5.5 and Claude Opus 4.7. Two-agent screening advances more applications (33.3% to 39.3% for GPT-5.5; 34.0% to 35.5% for Opus 4.7). Across three runs on the common 191-pair borderline pool, pass-instance rates rise from 4.5% to 26.2% and from 6.5% to 16.1%, respectively. This is not a uniform relaxation: two-agent screening rejects applications one-call advances, changing decisions in both directions. At similar pass volumes, the procedures advance different applications, and no one-call threshold recovers applications consistently selected by two-agent screening. Among discovery-selected cases re-executed in fresh runs, two-agent-only selections recur less often than shared selections, clearly under GPT-5.5 and less certainly under Opus 4.7, while a separate one-call follow-up shows no comparable decline. As hiring becomes agent-mediated on both sides, the screening procedure, not only the model behind it, shapes who reaches human review and how reliably that access recurs.