mlsanityData to 14 Oct 2026

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

arXiv 2603.16215 ↗First posted 17 Mar 2026cs.MA cs.AIcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 25 of its 39 references that are in the map. First posted on arXiv 17 Mar 2026.

Builds on

25 of 39 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screening1 Apr
  2. 2024Improving Multi-Agent Debate with Sparse Communication Topology17 Jun
  3. 2024TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models25 Mar
  4. 2024TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation15 Feb

Other references · 21

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  6. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  7. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  8. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
  9. 2015A Neural Conversational Modelcited by 196
  10. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 164
  11. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  12. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
9 more
  1. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 138
  2. 2023Verbosity Bias in Preference Labeling by Large Language Modelscited by 91
  3. 2025Learning to Reason for Long-Form Story Generationcited by 34
  4. 2024See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknessescited by 15
  5. 2024MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruitingcited by 8
  6. 2025FAIRE: Assessing Racial and Gender Bias in AI-Driven Resume Evaluationscited by 5
  7. 2024Mathematics of multi-agent learning systems at the interface of game theory and artificial intelligencecited by 1
  8. 2025Exploring the Implementation of AI in Early Onset Interviews to Help Mitigate Biascited by 1
  9. 2025Zara: An LLM-based Candidate Interview Feedback Systemcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscapecited by 4
  2. 2026PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessmentcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring
  2. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
  3. 2025MAGI: Multi-Agent Guided Interview for Psychiatric Assessment
  4. 2026A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models
  5. 2025CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring
  6. 2026Orchestrating LLM Agents for Scientific Research: A Pilot Study of Multiple Choice Question (MCQ) Generation and Evaluation
  7. 2025When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs
  8. 2026Asking Questions the Right Way: A Multi-Agent Conversational System for Prompt Formulation in Complex Task Resolution