When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening

2026-09-16

AI Summary

研究通过使用两个代理（雇主侧和候选人侧）在简历筛选中交换证据并更新判断，以提高筛选的公平性和准确性，相比单次静态判断方法，这种方法能够更有效地筛选出合适的候选人。

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.

Problem

• two-agent screening
• resume-job pairs
• access and recurrence

Innovation

• two-agent screening
• GPT-5.5
• Claude Opus 4.7
• resume-job pairs
• recurrence