CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation

2026-03-17

AI Summary

This work addresses the lack of robustness and fairness in AI-driven interview evaluation by proposing the first multi-agent collaborative framework that integrates multi-layered security defenses, adaptive difficulty adjustment, and rubric-based scoring. The architecture employs four specialized agents—responsible for question generation, safety enforcement, scoring, and summarization—orchestrated through a centralized finite-state machine to enable modular task decomposition. This design ensures a secure, multidimensional, and structured assessment process. Experimental results demonstrate that the system achieves strong performance in accuracy (90.47%), recall (83.33%), and candidate satisfaction (84.41%), while significantly mitigating subjective bias, thereby validating both the efficacy of the approach and its acceptability to users.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Large-scale security measurements

Abstract

Ensuring robust and fair interview assessment remains a key challenge in AI-driven evaluation. This paper presents CoMAI, a general-purpose multi-agent interview framework designed for diverse assessment scenarios. In contrast to monolithic single-agent systems based on large language models (LLMs), CoMAI employs a modular task-decomposition architecture coordinated through a centralized finite-state machine. The system comprises four agents specialized in question generation, security, scoring, and summarization. These agents work collaboratively to provide multi-layered security defenses against prompt injection, support multidimensional evaluation with adaptive difficulty adjustment, and enable rubric-based structured scoring that reduces subjective bias. Experimental results demonstrate that CoMAI achieved 90.47% accuracy, 83.33% recall, and 84.41% candidate satisfaction. These results highlight CoMAI as a robust, fair, and interpretable paradigm for AI-driven interview assessment.

Problem

• interview evaluation
• fairness
• robustness
• subjective bias
• prompt injection

Innovation

• multi-agent framework
• modular task decomposition
• prompt injection defense
• rubric-based scoring
• adaptive difficulty adjustment