MLAR: Multi-layer Large Language Model-based Robotic Process Automation Applicant Tracking

2025-07-14

AI Summary

Traditional recruitment faces bottlenecks in resume screening and shortlisting due to labor-intensive processes and limited human resources. To address this, we propose a three-tier large language model (LLM)-driven recruitment automation system that deeply integrates semantic understanding into robotic process automation (RPA). The first tier parses job descriptions; the second performs structured extraction of key information from resumes; and the third enables high-precision candidate–job matching via semantic similarity computation. This architecture overcomes RPA’s inherent limitations in handling unstructured text, enabling end-to-end automation of parsing, matching, and candidate notification. Experimental evaluation on 2,400 resumes demonstrates an average processing time of 5.4 seconds per resume—16.9% faster than Automation Anywhere and 17.1% faster than UiPath—while significantly improving both scalability and matching accuracy in large-scale recruitment scenarios.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

This paper introduces an innovative Applicant Tracking System (ATS) enhanced by a novel Robotic process automation (RPA) framework or as further referred to as MLAR. Traditional recruitment processes often encounter bottlenecks in resume screening and candidate shortlisting due to time and resource constraints. MLAR addresses these challenges employing Large Language Models (LLMs) in three distinct layers: extracting key characteristics from job postings in the first layer, parsing applicant resume to identify education, experience, skills in the second layer, and similarity matching in the third layer. These features are then matched through advanced semantic algorithms to identify the best candidates efficiently. Our approach integrates seamlessly into existing RPA pipelines, automating resume parsing, job matching, and candidate notifications. Extensive performance benchmarking shows that MLAR outperforms the leading RPA platforms, including UiPath and Automation Anywhere, in high-volume resume-processing tasks. When processing 2,400 resumes, MLAR achieved an average processing time of 5.4 seconds per resume, reducing processing time by approximately 16.9% compared to Automation Anywhere and 17.1% compared to UiPath. These results highlight the potential of MLAR to transform recruitment workflows by providing an efficient, accurate, and scalable solution tailored to modern hiring needs.

Problem

• Automates resume screening and candidate shortlisting using LLMs
• Integrates RPA with semantic matching for efficient recruitment
• Reduces processing time in high-volume resume tasks significantly

Innovation

• Multi-layer LLM for resume and job parsing
• Semantic algorithms for candidate-job matching
• Integration with RPA for automated recruitment