EVALPRO: A Comprehensive AI-Based Platform for Simulated Recruitment and Skill Assessment. An intelligent system designed to automate end-to-end mock hiring, enabling realistic candidate evaluation and performance analysis

DOI

10.2991/978-94-6239-723-1_3How to use a DOI?

Keywords

AI-Powered Candidate Evaluation; Natural Language Processing; Adaptive Testing; Large Language Models; Sandbox Execution; Multimodal Assessment

Abstract

EVALPRO is a platform that helps with the hiring process. It does this by simulating the process of finding and hiring someone. This includes testing how smart someone is, how good they are at their job and how well they do in interviews with people from the company and with the human resources department. The people looking for a job and the people doing the hiring both get feedback from EVALPRO. EVAL- PRO is also very secure. It can run code in an environment and tell the person what the code does. The system can look at kinds of information including text, audio and video. This helps the people doing the hiring get a sense of who the person is and if they are a good fit for the job. EVALPRO is about making the hiring process easier and more effective, for everyone involved. To enhance the reliability, safety, and consistency of LLM-driven components, EVALPRO incorporates runtime guardrails, including constrained decoding strategies, template-first generation, functional evaluation heuristics, and sandboxed execution with inverse overlay analysis. This paper presents the overall system architecture, core algorithms, runtime safety mechanisms, and an evaluation framework. Pilot study results demonstrate the feasibility of the proposed approach in realistic recruitment scenarios and highlight directions for future improvements in robustness, fairness, and scalability.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sumaira A. Shaikh
AU  - Pratima Patil
AU  - Danish Bhat
AU  - Prathamesh Bharsakale
AU  - Ayush Bhagwat
PY  - 2026
DA  - 2026/07/14
TI  - EVALPRO: A Comprehensive AI-Based Platform for Simulated Recruitment and Skill Assessment. An intelligent system designed to automate end-to-end mock hiring, enabling realistic candidate evaluation and performance analysis
BT  - Proceedings of the International Conference on Responsible, Risk-aware, and Regulated AI (RRRAI 2026)
PB  - Atlantis Press
SP  - 15
EP  - 29
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-723-1_3
DO  - 10.2991/978-94-6239-723-1_3
ID  - Shaikh2026
ER  -