Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.16215 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918393393709056 |
|---|---|
| author | Sun, Gengxin Yu, Ruihao Yin, Liangyi Yang, Yunqi Zhang, Bin Xu, Zhiwei |
| author_facet | Sun, Gengxin Yu, Ruihao Yin, Liangyi Yang, Yunqi Zhang, Bin Xu, Zhiwei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16215 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation Sun, Gengxin Yu, Ruihao Yin, Liangyi Yang, Yunqi Zhang, Bin Xu, Zhiwei Multiagent Systems Artificial Intelligence I.2.11; K.3.1; D.4.6 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. |
| title | CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation |
| topic | Multiagent Systems Artificial Intelligence I.2.11; K.3.1; D.4.6 |
| url | https://arxiv.org/abs/2603.16215 |