Metraipolis › archive › dc_702bf820d4b4
When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening — arXiv:2609.19530
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19530
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:20:03.885Z
- SHA-256 of the archived text
8e28bff695b2eada95a8e65acf72a3b39a4f1c51b076c6bf7866e8b2a814050d- Stable URL of this page
https://metraipolis.com/documento/dc_702bf820d4b4
How to cite
When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening — arXiv:2609.19530 — arXiv (en), https://arxiv.org/abs/2609.19530 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_702bf820d4b4 (Metraipolis archive dc_702bf820d4b4, sha256 8e28bff695b2eada95a8e65acf72a3b39a4f1c51b076c6bf7866e8b2a814050d)
BibTeX
@misc{dc702bf820d4b4,
title = {When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening — arXiv:2609.19530},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19530},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_702bf820d4b4; sha256 8e28bff695b2eada95a8e65acf72a3b39a4f1c51b076c6bf7866e8b2a814050d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19530. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.19530 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:04:13.616Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).