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.