# AI-Driven Decision-Making System for Hiring Process

arXiv: https://arxiv.org/abs/2512.20652 · HTML: https://mlsanity.com/paper/2512.20652/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [CultureLLM: Incorporating Cultural Differences into Large Language Models](https://mlsanity.com/paper/2402.10946/) (2024)
- [CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks](https://mlsanity.com/paper/2507.10535/) (2025)
- [AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screening](https://mlsanity.com/paper/2504.02870/) (2025)
- [Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration](https://mlsanity.com/paper/2312.03987/) (2023)
- [AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers](https://mlsanity.com/paper/2410.01824/) (2024)
- [End-to-End Resume Parsing and Finding Candidates for a Job Description using BERT](https://mlsanity.com/paper/1910.03089/) (2019)
- [Toward Verifiable Misinformation Detection: A Multi-Tool LLM Agent Framework](https://mlsanity.com/paper/2508.03092/) (2025)
- [Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models](https://mlsanity.com/paper/2508.16673/) (2025)
- [StepGrade: Grading Programming Assignments with Context-Aware LLMs](https://mlsanity.com/paper/2503.20851/) (2025)
- [Smart-Hiring: An Explainable end-to-end Pipeline for CV Information Extraction and Job Matching](https://mlsanity.com/paper/2511.02537/) (2025)
- [It Hears, It Sees too: Multi-Modal LLM for Depression Detection By Integrating Visual Understanding into Audio Language Models](https://mlsanity.com/paper/2511.19877/) (2025)

## Abstract (arXiv)

Early-stage candidate validation is a major bottleneck in hiring, because recruiters must reconcile heterogeneous inputs (resumes, screening answers, code assignments, and limited public evidence). This paper presents an AI-driven, modular multi-agent hiring assistant that integrates (i) document and video preprocessing, (ii) structured candidate profile construction, (iii) public-data verification, (iv) technical/culture-fit scoring with explicit risk penalties, and (v) human-in-the-loop validation via an interactive interface. The pipeline is orchestrated by an LLM under strict constraints to reduce output variability and to generate traceable component-level rationales. Candidate ranking is computed by a configurable aggregation of technical fit, culture fit, and normalized risk penalties. The system is evaluated on 64 real applicants for a mid-level Python backend engineer role, using an experienced recruiter as the reference baseline and a second, less experienced recruiter for additional comparison. Alongside precision/recall, we propose an efficiency metric measuring expected time per qualified candidate. In this study, the system improves throughput and achieves 1.70 hours per qualified candidate versus 3.33 hours for the experienced recruiter, with substantially lower estimated screening cost, while preserving a human decision-maker as the final authority.