PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment

Jul 16, 2026

Upload by Asher

PolyInterview delivers immersive mock interview practice by generating role- and candidate-tailored questions from a target job description and a CV. It supports multi-turn spoken interviews with a lip-synced digital human interviewer, where LLM agents produce answer-aware follow-up questions. Comprehensive evaluation spans response content, vocal delivery, and non-verbal behavior, producing 13 behavior-level features aggregated into 10 assessment aspects and two competency tracks. The report maps scores to evidence via KSA and STAR and provides actionable recommendations, with public deployment statistics and expert validation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

Abstract

Introduction

Problem and motivation

Related work limitations

PolyInterview system overview

PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment Zhiyuan Wen 1 , Jiannong Cao 1 , Zijian Wang 1 , Chen Chen 1 , Xiaoyun Liu 1 , Jianing Yin 1 , Zhuo Li2 1Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China 2 School of Artificial Intelligence, Chongqing University of Posts and Telecommunications, China {zyuanwen, jiannong.cao, [zi-jian.wang}@polyu.edu.hk](zi-jian.wang}@polyu.edu.hk)[ ](zi-jian.wang}@polyu.edu.hk){chen03.chen, xiaoyun.liu, [jianing-laetitia.yin}@connect.polyu.hk](jianing-laetitia.yin}@connect.polyu.hk) [cliff.zhuo.li@gmail.com](cliff.zhuo.li@gmail.com) arXiv :2607 . 103 10v 1 [ cs .CL] 11 Jul 2026 Abstract Preparing for job interviews is important for securing desired positions, yet realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor structured assessment. Existing systems typically address only parts of this need through fixed question sequences, limited communication channels, or feedback with little supporting evidence. We present PolyInterview, an LLMbased platform for immersive mock interview practice with comprehensive multimodal assessment. PolyInterview uses the target job description and CV to generate questions tailored to the role and candidate, conducts multi-turn spoken interviews with a lip-synced digital human interviewer that asks answer-aware followup questions, and evaluates response content, vocal delivery, and non-verbal behavior. Four parallel evaluators produce 13 behavior-level features that are aggregated into 10 assessment aspects and two competency tracks. Guided by the KSA and STAR frameworks, the report links each score to behavioral evidence and actionable recommendations. PolyInterview is publicly accessible 1. Its current allaccount snapshot contains 101 accounts, 1,564 interview sessions, 7,665 generated questions, and 1,422 five-stage question sets. Generated questions are more closely aligned with their matched job description than with cross-role job descriptions in 93.7% of sessions. An evaluation by ten experts found strong question plans and actionable feedback. 1 Introduction Effective preparation for job interviews is critical to securing a desired position. During an interview, both candidates’ role-relevant knowledge and skills and their ability to communicate experience 1PolyInterview is deployed for public access. The demo video and system link are available here. Figure 1: PolyInterview’s workflow, from personalized setup and immersive interviewing to multimodal assessment and comprehensive reporting and feedback. and reasoning clearly are evaluated. Despite the importance of interview preparation, realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor structured assessment. These constraints motivate an accessible platform that can simulate multi-turn interview interactions and provide comprehensive assessment and feedback. Commercial products and research prototypeshave expanded access to interview practice, yet, as summarized in Table 1, they do not jointly support role-conditioned multi-stage questioning, answeraware probing, and theory-grounded assessment of textual, vocal, and non-verbal behavior within an integrated practice environment. For commercial tools, products such as Google Interview Warmup, Yoodli, and Big Interview support question rehearsal or automated feedback, but generally rely on fixed question sequences, assess only selected communication channels, or provide limited trans- parency into how feedback is derived. For research prototypes, virtual interview agents have explored conversational realism (Hoque et al., 2013 ; Anderson et al., 2013 ; Smith et al., 2014); LLM-based mock interviewers support

FAQs

How does PolyInterview personalize mock interview questions?

PolyInterview uses the target job description and the candidate’s CV to generate questions tailored to the role and the candidate. It then uses answer-aware follow-up generation for multi-turn interaction.

What modalities does PolyInterview assess during the interview?

PolyInterview evaluates response content, vocal delivery, and non-verbal behavior. It combines LLM-based analysis for content, speech analysis, and VLM-based analysis for non-verbal cues.

How are interview results scored and reported to the user?

Four parallel evaluators extract 13 behavior-level features, which are aggregated into 10 assessment aspects and two competency tracks. Scores are linked to behavioral evidence using the KSA and STAR frameworks, along with actionable recommendations.

Jul 16, 2026

Upload by Asher