Skip to content
AI News HubLIVE
Original source2 min read

From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance

Summary

This systematized narrative review traces AI recruitment from bilateral retrieval and behavioral ranking through neural person–job matching, LLM components, and tool-using recruiting agents. It analyzes three coupled transitions—similarity to reciprocal suitability, model to compound workflow, and offline prediction to evidence- and productivity-aligned evaluation—and identifies persistent gaps in behavioral labels, external validity, pipeline-level evaluation, and joint privacy-security assessment, proposing a staged evidence-to-claim mapping and an agenda for auditable systems.

SourcearXiv AIAuthor: Ziyi Zhao, Guanzheng Wei
From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 3 Sep 2026]

Title:From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance

View a PDF of the paper titled From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance, by Ziyi Zhao and Guanzheng Wei

View PDF HTML (experimental)

Abstract:Artificial intelligence in recruitment has shifted the object being automated from profile pairs and ranked lists to multi-stage workflows that retrieve evidence, compare candidates, and support or execute actions. This systematized narrative review traces that development from bilateral retrieval and behavioral ranking through neural person--job matching, large language model (LLM) components, and tool-using recruiting agents. Using a purposive search and coding protocol updated through 23 July 2026, plus targeted updates through 2 September 2026, we organize 40 representative works with supporting industrial and legal sources. This synthesis is not a prevalence estimate. We analyze three coupled transitions: from similarity to reciprocal suitability, from a model to a compound workflow, and from offline prediction to evidence- and productivity-aligned evaluation. Across document understanding, retrieval, ranking, assessment, interviewing, sourcing, and human handoff, we distinguish field-, pair-, list-, case-, trajectory-, and outcome-level evidence. Persistent gaps arise because behavioral labels confound exposure, preference, and qualification; private and synthetic data limit external validity; final-output scores conceal pipeline failures; and, within the coded set, privacy is not directly evaluated and no row jointly evaluates utility, fairness, privacy, and security. These observations describe the coded set rather than the field as a whole. We therefore introduce a staged mapping from evaluation evidence to the strongest defensible claim, together with an agenda for reciprocal, evidence-grounded, temporally controlled, selective, and auditable systems. Progress should be judged by whether workflows retrieve the right evidence, preserve uncertainty, support contestable decisions, and improve outcomes under explicit cost and risk constraints.

Comments: 53 pages, 4 figures, 10 tables; companion literature-coding and search-log CSVs included in the source package

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.04286 [cs.AI]

(or arXiv:2609.04286v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.04286

arXiv-issued DOI via DataCite

Submission history

From: Guanzheng Wei [view email] [v1] Thu, 3 Sep 2026 08:46:03 UTC (84 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance, by Ziyi Zhao and Guanzheng Wei

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • AI recruitment has shifted from automating profile pairs and ranked lists to multi-stage workflows that retrieve evidence, compare candidates, and support or execute actions.
  • The review identifies three coupled transitions: similarity to reciprocal suitability, model to compound workflow, and offline prediction to evidence- and productivity-aligned evaluation.
  • Key gaps include behavioral labels confounding exposure, preference, and qualification; limited external validity from private and synthetic data; final scores concealing pipeline failures; and no joint evaluation of utility, fairness, privacy, and security.
  • The authors propose a staged mapping from evaluation evidence to the strongest defensible claim and an agenda for reciprocal, evidence-grounded, temporally controlled, selective, and auditable systems.

Highlights and analysis are generated automatically and may contain errors. Check the original source.