{"slug": "from-matching-models-to-recruiting-agents-a-systematized-narrative-review-of-ai", "title": "From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance", "summary": "A systematized narrative review of 40 representative AI recruitment systems, updated through 2 September 2026, finds that the field has shifted from matching profiles to multi-stage workflows using large language models and tool-using recruiting agents, but persistent gaps remain: privacy is not directly evaluated and no study jointly evaluates utility, fairness, privacy, and security. The authors propose a staged mapping from evaluation evidence to defensible claims and an agenda for reciprocal, evidence-grounded, temporally controlled, selective, and auditable systems.", "body_md": "arXiv:2609.04286v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/from-matching-models-to-recruiting-agents-a-systematized-narrative-review-of-ai", "canonical_source": "https://arxiv.org/abs/2609.04286", "published_at": "2026-09-07 04:00:00+00:00", "updated_at": "2026-09-07 04:28:11.149525+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-ethics", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/from-matching-models-to-recruiting-agents-a-systematized-narrative-review-of-ai", "markdown": "https://wpnews.pro/news/from-matching-models-to-recruiting-agents-a-systematized-narrative-review-of-ai.md", "text": "https://wpnews.pro/news/from-matching-models-to-recruiting-agents-a-systematized-narrative-review-of-ai.txt", "jsonld": "https://wpnews.pro/news/from-matching-models-to-recruiting-agents-a-systematized-narrative-review-of-ai.jsonld"}}