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

arXiv: https://arxiv.org/abs/2609.04286 · HTML: https://mlsanity.com/paper/2609.04286/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 127 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 18 of 18)

- [xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations](https://mlsanity.com/paper/2506.13651/) (2025)
- [Job Recommender Systems: A Review](https://mlsanity.com/paper/2111.13576/) (2021)
- [AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insights](https://mlsanity.com/paper/2509.00462/) (2025)
- [MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruiting](https://mlsanity.com/paper/2405.18113/) (2024)
- [FAIRE: Assessing Racial and Gender Bias in AI-Driven Resume Evaluations](https://mlsanity.com/paper/2504.01420/) (2025)
- [JobResQA: A Benchmark for LLM Machine Reading Comprehension on Multilingual R'esum'es and JDs](https://mlsanity.com/paper/2601.23183/) (2026)
- [Measuring Validity in LLM-based Resume Screening](https://mlsanity.com/paper/2602.18550/) (2026)
- [PJB: A Reasoning-Aware Benchmark for Person-Job Retrieval](https://mlsanity.com/paper/2603.17386/) (2026)
- [ConFit v3: Improving Resume-Job Matching with LLM-based Re-Ranking](https://mlsanity.com/paper/2605.09760/) (2026)
- [PeopleSearchBench: Evaluating AI-Powered People Search Platforms with Criteria-Grounded Verification](https://mlsanity.com/paper/2603.27476/) (2026)
- [JobHop v2: A Large-Scale Career Trajectory Dataset from Unstructured Resumes](https://mlsanity.com/paper/2607.11715/) (2026)
- [STEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling](https://mlsanity.com/paper/2607.11722/) (2026)
- [Applied and Filtered: An End-to-End Algorithmic Fairness Audit of A Public Employment Agency](https://mlsanity.com/paper/2608.13022/) (2026)
- [Fairness Hazard Analysis for Socio-Technical Processes: A Multiple-Case Study in Bias-sensitive Organisational Settings](https://mlsanity.com/paper/2608.22978/) (2026)
- [An Interactive Agent for Requirement-Driven Candidate Sourcing](https://mlsanity.com/paper/2608.23501/) (2026)
- [Mitigating Fabrication in Multi-Stage LLM Pipelines for Hiring: An Empirical Evaluation of Prompt Guardrails and Human-in-the-Loop Checkpoints](https://mlsanity.com/paper/2608.26171/) (2026)
- [LongPIBench: A Long-Context Benchmark for Prompt Injection](https://mlsanity.com/paper/2608.28411/) (2026)
- [Applications of Risk Science to AI Fairness Evaluation: Principles, Challenges, and Best Practices](https://mlsanity.com/paper/2608.29478/) (2026)

## Abstract (arXiv)

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.