Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring
For developers of LLM-based tutoring systems, this work provides an architecture that maintains doctrinal fidelity while enabling productive dialectical reasoning.
The paper addresses the problem of semantic drift and dialectical stagnation in LLM-based multi-agent systems for ethical tutoring. The proposed Heterogeneous Debate Engine (HDE) architecture, combining Identity-Grounded RAG and Heuristic Theory of Mind, increased Argument Complexity Scores by an order of magnitude compared to baselines.
Large Language Models (LLMs) are being increasingly used as autonomous agents in complex reasoning tasks, opening the niche for dialectical interactions. However, Multi-Agent systems implemented with systematically unconstrained systems systematically undergo semantic drift and logical deterioration and thus can hardly be used in providing ethical tutoring where a precise answer is required. Current simulation often tends to degenerate into dialectical stagnation, the agents degenerate into recursive concurrence or circular arguments. A critical challenge remains: how to enforce doctrinal fidelity without suppressing the generative flexibility required for dialectical reasoning? To address this niche, we contribute the Heterogeneous Debate Engine (HDE), a cognitive architecture that combines Identity-Grounded Retrieval-Augmented Generation (ID-RAG) for doctrinal fidelity and Heuristic Theory of Mind for strategic opponent modeling. Our evaluation shows that architectural heterogeneity is a crucial variable to stability: contrary doctrinal initializations (e.g., Deontology vs. Utilitarianism) have increased the Argument Complexity Scores of students by an order of magnitude, over baselines. These findings validate the effectiveness of ID-RAG and Heuristic ToM as architectural requirements in maintaining high-fidelity (adversarial) pedagogy.