MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruiting

TL;DR

MockLLM introduces a multi-agent framework using large language models to simulate and evaluate interactive job interviews, improving online recruitment matching accuracy and adaptability.

Contribution

The paper presents a novel multi-agent LLM-based framework for generating and assessing mock interviews, enhancing person-job matching in online recruitment platforms.

Findings

Outperforms existing methods in matching accuracy

Demonstrates scalability across job domains

Enhances candidate assessment through interactive simulation

Abstract

Online recruitment platforms have reshaped job-seeking and recruiting processes, driving increased demand for applications that enhance person-job matching. Traditional methods generally rely on analyzing textual data from resumes and job descriptions, limiting the dynamic, interactive aspects crucial to effective recruitment. Recent advances in Large Language Models (LLMs) have revealed remarkable potential in simulating adaptive, role-based dialogues, making them well-suited for recruitment scenarios. In this paper, we propose \textbf{MockLLM}, a novel framework to generate and evaluate mock interview interactions. The system consists of two key components: mock interview generation and two-sided evaluation in handshake protocol. By simulating both interviewer and candidate roles, MockLLM enables consistent and collaborative interactions for real-time and two-sided matching. To further improve the matching quality, MockLLM further incorporates reflection memory generation and dynamic strategy modification, refining behaviors based on previous experience. We evaluate MockLLM on real-world data Boss Zhipin, a major Chinese recruitment platform. The experimental results indicate that MockLLM outperforms existing methods in matching accuracy, scalability, and adaptability across job domains, highlighting its potential to advance candidate assessment and online recruitment.