Home / Current Issue / Paper 1713210
Multi-Agent Debate System for AI-Based Decision-Making: A Framework for Enhanced Reasoning Through Collaborative Intelligence
Subject area: Science,Engineering and Technology · Area of research: Multi-Agent AI-Based Decision-Making
Abstract
Single-agent Large Language Models (LLMs) demonstrate limitations in complex decisionmaking scenarios, including domain-specific bias, overconfidence, and inability to integrate diverse perspectives. This paper presents the MultiAgent Debate System (MADS), a collaborative AI architecture leveraging specialized agents to generate robust insights through structured argumentation. Implemented using CrewAI framework with Llama 3 models via Groq's LPU infrastructure, MADS orchestrates three specialized agents (Advocate, Critic, Judge) in sequential debate workflows. Testing on interdisciplinary datasets demonstrates 73% improvement in argument quality over singleagent baselines, with average response generation under 8 seconds. The system produces multi-format outputs (transcripts, summaries, PDF reports) accessible to nontechnical users. By replicating human deliberative processes through agent-based debate, MADS advances interpretable, transparent AI decision-support systems while addressing critical gaps in crossdomain reasoning and perspective integration.
Keywords
Multi-Agent Systems, Large Language Models, Computational Argumentation, Decision Support Systems, Collaborative AI
References
[1] T. B. Brown et al., "Language models are fewshot learners," Advances in Neural Information Processing Systems, vol. 33, pp. 1877-1901, 2020.
[2] H. Touvron et al., "Llama 2: Open foundation and fine-tuned chat models," arXiv preprint arXiv:2307.09288, 2023.
[3] R. Bommasani et al., "On the opportunities and risks of foundation models," arXiv preprint arXiv:2108.07258, 2021.
[4] J. Wei et al., "Chain-of-thought prompting elicits reasoning in large language models," Advances in NeurIPS, vol. 35, pp. 24824-24837, 2022.
[5] M. Wooldridge, An Introduction to MultiAgent Systems, 2nd ed., Wiley, 2009.
[6] Y. Talebirad and A. Nadiri, "Multi-agent collaboration: Harnessing intelligent LLM agents," arXiv preprint arXiv:2306.03314, 2023.
[7] G. Li et al., "CAMEL: Communicative agents for mind exploration of large scale language model society," Advances in NeurIPS, vol. 36, 2023.
[8] J. S. Park et al., "Generative agents: Interactive simulacra of human behavior," Proc. ACM UIST, pp. 1-22, 2023.
[9] G. Irving, P. Christiano, and D. Amodei, "AI safety via debate," arXiv preprint arXiv:1805.00899, 2018.
[10] Y. Du et al., "Improving factuality and reasoning through multiagent debate," arXiv preprint arXiv:2305.14325, 2023.
[11] P. Lewis et al., "Retrieval-augmented generation for knowledge-intensive NLP tasks," Advances in NeurIPS, vol. 33, pp. 9459-9474, 2020.
[12] Y. Gao et al., "Retrieval-augmented generation for large language models: A survey," arXiv preprint arXiv:2312.10997, 2024.
How to cite this paper
@article{1713210,
author = {Aakriti Dhar Dubey, Piyush Kumar Jha, Anushka Bohra, Pancham Kumar Singh, Dr. Anurag Upadhyay},
title = {Multi-Agent Debate System for AI-Based Decision-Making: A Framework for Enhanced Reasoning Through Collaborative Intelligence},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {6},
pages = {2258-2262},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1713210.pdf},
abstract = {Single-agent Large Language Models (LLMs) demonstrate limitations in complex decisionmaking scenarios, including domain-specific bias, overconfidence, and inability to integrate diverse perspectives. This paper presents the MultiAgent Debate System (MADS), a collaborative AI architecture leveraging specialized agents to generate robust insights through structured argumentation. Implemented using CrewAI framework with Llama 3 models via Groq's LPU infrastructure, MADS orchestrates three specialized agents (Advocate, Critic, Judge) in sequential debate workflows. Testing on interdisciplinary datasets demonstrates 73% improvement in argument quality over singleagent baselines, with average response generation under 8 seconds. The system produces multi-format outputs (transcripts, summaries, PDF reports) accessible to nontechnical users. By replicating human deliberative processes through agent-based debate, MADS advances interpretable, transparent AI decision-support systems while addressing critical gaps in crossdomain reasoning and perspective integration. },
keywords = {Multi-Agent Systems, Large Language Models, Computational Argumentation, Decision Support Systems, Collaborative AI},
month = {December},
doi = {https://doi.org/10.64388/IREV9I6-1713210}
}