Topic
multi-agent system
CAF-Gen Multi-Agent System Enhances Argumentation Structures with Iterative Pipeline
CAF-Gen is a novel multi-agent framework that enriches shallow argumentation structures into Carneades Argumentation Framework (CAF)-compliant models using an iterative Creator-Reviewer pipeline. The system addresses limitations of single-pass generative models by improving structural integrity and alignment with original annotations.
DeepRoot Multi-Agent System Enables Therapeutic Reasoning Over Historical Medical Texts with 47.6% Accuracy
DeepRoot is a multi-agent LLM system that jointly builds and utilizes a verified knowledge graph for therapeutic reasoning over historical medical texts. Applied to the Shen Nong Ben Cao Jing, it recovers 10 of 21 held-out compound-disease treatment pairs at R@20 (47.6%), significantly outperforming a raw corpus LLM (4.8%) and random baseline (2.4%). The system also reduces hallucination to 7-10% compared to 87% for tool-using LLMs, offering a scalable method for mining historical medical knowledge.