@inproceedings{yuksel-etal-2026-agentic,
title = "Agentic {AI} for Human Resources: {LLM}-Driven Candidate Assessment",
author = "Yuksel, Kamer Ali and
Anees, Abdul Basit and
Elneima, Ashraf Hatim and
Hewavitharana, Sanjika and
Al-Badrashiny, Mohamed and
Sawaf, Hassan",
editor = "Croce, Danilo and
Leidner, Jochen and
Moosavi, Nafise Sadat",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
month = mar,
year = "2026",
address = "Rabat, Marocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-demo.24/",
pages = "341--348",
ISBN = "979-8-89176-382-1",
abstract = "In this work, we present a modular and interpretable framework that uses Large Language Models (LLMs) to automate candidate assessment in recruitment. The system integrates diverse sources{---}including job descriptions, CVs, interview transcripts, and HR feedback{---}to generate structured evaluation reports that mirror expert judgment. Unlike traditional ATS tools that rely on keyword matching or shallow scoring, our approach employs role-specific, LLM-generated rubrics and a multi-agent architecture to perform fine-grained, criteria-driven evaluations. The framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring workflows. Beyond rubric-based analysis, we introduce an LLM-Driven Active Listwise Tournament mechanism for candidate ranking. Instead of noisy pairwise comparisons or inconsistent independent scoring, the LLM ranks small candidate subsets ({``}mini-tournaments''), and these listwise permutations are aggregated using a Plackett{--}Luce model. An active-learning loop selects the most informative subsets, producing globally coherent and sample-efficient rankings. This adaptation of listwise LLM preference modeling{---}previously explored in financial asset ranking {---}provides a principled and highly interpretable methodology for large-scale candidate ranking in talent acquisition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuksel-etal-2026-agentic">
<titleInfo>
<title>Agentic AI for Human Resources: LLM-Driven Candidate Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamer</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Yuksel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="given">Basit</namePart>
<namePart type="family">Anees</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashraf</namePart>
<namePart type="given">Hatim</namePart>
<namePart type="family">Elneima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjika</namePart>
<namePart type="family">Hewavitharana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Al-Badrashiny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Croce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jochen</namePart>
<namePart type="family">Leidner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="given">Sadat</namePart>
<namePart type="family">Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Marocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-382-1</identifier>
</relatedItem>
<abstract>In this work, we present a modular and interpretable framework that uses Large Language Models (LLMs) to automate candidate assessment in recruitment. The system integrates diverse sources—including job descriptions, CVs, interview transcripts, and HR feedback—to generate structured evaluation reports that mirror expert judgment. Unlike traditional ATS tools that rely on keyword matching or shallow scoring, our approach employs role-specific, LLM-generated rubrics and a multi-agent architecture to perform fine-grained, criteria-driven evaluations. The framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring workflows. Beyond rubric-based analysis, we introduce an LLM-Driven Active Listwise Tournament mechanism for candidate ranking. Instead of noisy pairwise comparisons or inconsistent independent scoring, the LLM ranks small candidate subsets (“mini-tournaments”), and these listwise permutations are aggregated using a Plackett–Luce model. An active-learning loop selects the most informative subsets, producing globally coherent and sample-efficient rankings. This adaptation of listwise LLM preference modeling—previously explored in financial asset ranking —provides a principled and highly interpretable methodology for large-scale candidate ranking in talent acquisition.</abstract>
<identifier type="citekey">yuksel-etal-2026-agentic</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-demo.24/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>341</start>
<end>348</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Agentic AI for Human Resources: LLM-Driven Candidate Assessment
%A Yuksel, Kamer Ali
%A Anees, Abdul Basit
%A Elneima, Ashraf Hatim
%A Hewavitharana, Sanjika
%A Al-Badrashiny, Mohamed
%A Sawaf, Hassan
%Y Croce, Danilo
%Y Leidner, Jochen
%Y Moosavi, Nafise Sadat
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Marocco
%@ 979-8-89176-382-1
%F yuksel-etal-2026-agentic
%X In this work, we present a modular and interpretable framework that uses Large Language Models (LLMs) to automate candidate assessment in recruitment. The system integrates diverse sources—including job descriptions, CVs, interview transcripts, and HR feedback—to generate structured evaluation reports that mirror expert judgment. Unlike traditional ATS tools that rely on keyword matching or shallow scoring, our approach employs role-specific, LLM-generated rubrics and a multi-agent architecture to perform fine-grained, criteria-driven evaluations. The framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring workflows. Beyond rubric-based analysis, we introduce an LLM-Driven Active Listwise Tournament mechanism for candidate ranking. Instead of noisy pairwise comparisons or inconsistent independent scoring, the LLM ranks small candidate subsets (“mini-tournaments”), and these listwise permutations are aggregated using a Plackett–Luce model. An active-learning loop selects the most informative subsets, producing globally coherent and sample-efficient rankings. This adaptation of listwise LLM preference modeling—previously explored in financial asset ranking —provides a principled and highly interpretable methodology for large-scale candidate ranking in talent acquisition.
%U https://aclanthology.org/2026.eacl-demo.24/
%P 341-348
Markdown (Informal)
[Agentic AI for Human Resources: LLM-Driven Candidate Assessment](https://aclanthology.org/2026.eacl-demo.24/) (Yuksel et al., EACL 2026)
ACL
- Kamer Ali Yuksel, Abdul Basit Anees, Ashraf Hatim Elneima, Sanjika Hewavitharana, Mohamed Al-Badrashiny, and Hassan Sawaf. 2026. Agentic AI for Human Resources: LLM-Driven Candidate Assessment. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 341–348, Rabat, Marocco. Association for Computational Linguistics.