Multi-Agent debate system based on large language models: structured deliberation and validation in satellite communications

Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges

This work presents a systematic literature review characterizing 141 primary studies on Multi-Agent Debate, and derives a three-dimensional taxonomy covering debate participants, the interaction mechanisms structuring the exchange, and the agreement protocols governing debate resolution, supported by formal notations to render MAD configurations.

Language Model Council: A Multi-Agent Framework using Explainable AI

This work introduces the Language Model Council (LMC), a collaborative framework that combines the expertise of multiple specialized AI agents to evaluate a user query from different perspectives and outperforms traditional single-model systems by improving response quality, reducing hallucinations, and increasing user trust through enhanced explainability.

ICMTEST-2026 - an Adaptive Multi-Agent Framework for Argumentation With a Legal Case Study

Performing complex, debate-oriented reasoning tasks does not only involve searching for information, but it also involves organizing the data into clear arguments and counterarguments. Traditional AI systems usually face problems in having a structured flow of arguments, and they fall apart when faced with cold-start conditions in the absence of precedents. To help meet these challenges, we propose an adaptive multi-agent framework that combines the principle of Retrieval-Augmented Generation (RAG) with structured debate and knowledge enrichment over time. This framework enables long-term learning and better performance over time, in contrast to the static systems that do not update their own knowledge base following a case. To illustrate the effectiveness of this framework, we present a case study of the problem involving a part of the Indian Penal Code. The system manages to mimic a trial between opposing parties, assess evidence, and give a thorough final report, including an overview of facts and a probable court ruling.

Integration of Multi-agent Reinforcement Learning (MARL) and Large Language Models (LLMs) in Agentic AI Systems: A Narrative Review

Quality Score: A Behavioural Metric for Deliberation Quality in LLM-MAS Systems

Autonomous systems increasingly employ Large Language Models (LLMs) as a deliberative layer in situations where classical machine learning methods encounter out-of-distribution scenarios. The use of multiple models in a multi-agent configuration (LLM-MAS) enables mutual validation of responses and reduces the risk of errors arising from the inherent biases of a single model. A fundamental question arises, however: what is the quality of the deliberation process in such a dialogue? This paper introduces Quality Score (Q)-a behavioural, post-hoc metric grounded in observable dialogue interaction patterns, assessing the quality of the deliberation process in LLM-MAS systems. Q is computed from four components: Position Evolution (PE), Argument Diversity (AD), Consensus Timing (CT), and Mutual Acknowledgment (MA). Validation was conducted on 303 dialogues across three experimental conditions differing in the presence of Dialogue Service Level Objectives (DSLO). Results show that Q captures meaningful differences in deliberation dynamics: unconstrained dialogues achieve an average $\mathbf{Q}=\mathbf{0. 7 9 5}$, while DSLO conditions yield $\mathbf{Q}=\mathbf{0. 7 0 2}$ and $\mathbf{Q}=\mathbf{0. 7 4 7}$, respectively. Given a sufficiently large statistical sample, Q enables identification of which system configurations systematically produce higher-quality deliberation-knowledge potentially useful when designing LLM-MAS systems for applications in automation and robotics.

Two Calls Beat Five Agents: Evaluating Multi-Agent Pipelines Against Self-Refinement for Local Language Models

It is demonstrated that communication format and implementation details determine outcomes more than architectural complexity, and that simpler approaches match or outperform multi-agent pipelines for local 7B model deployment.