@inproceedings{gao-jiang-2026-hiring,
title = "When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent R{\'e}sum{\'e} Screening",
author = "Gao, Jian and
Jiang, Hang",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.44/",
pages = "655--663",
ISBN = "979-8-89176-485-9",
abstract = "Hiring is bilateral: employers assess fit, while candidates present and defend evidence of their qualifications. Yet r{\'e}sum{\'e} screening{---}the first gate{---}is commonly automated as a static, one-call judgment over a r{\'e}sum{\'e}{--}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 r{\'e}sum{\'e}{--}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, 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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-jiang-2026-hiring">
<titleInfo>
<title>When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-485-9</identifier>
</relatedItem>
<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, 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.</abstract>
<identifier type="citekey">gao-jiang-2026-hiring</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.44/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>655</start>
<end>663</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening
%A Gao, Jian
%A Jiang, Hang
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F gao-jiang-2026-hiring
%X 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, 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.
%U https://aclanthology.org/2026.realm-1.44/
%P 655-663
Markdown (Informal)
[When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening](https://aclanthology.org/2026.realm-1.44/) (Gao & Jiang, REALM 2026)
ACL