# Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring

arXiv: https://arxiv.org/abs/2603.27404 · HTML: https://mlsanity.com/paper/2603.27404/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate](https://mlsanity.com/paper/2509.05396/) (2025)
- [Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate](https://mlsanity.com/paper/2402.07401/) (2024)
- [Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues](https://mlsanity.com/paper/2503.06424/) (2025)
- [Theory of Mind in Large Language Models: Assessment and Enhancement](https://mlsanity.com/paper/2505.00026/) (2025)
- [Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs](https://mlsanity.com/paper/2406.11514/) (2024)
- [Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems](https://mlsanity.com/paper/2509.10401/) (2025)
- [HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems](https://mlsanity.com/paper/2505.13516/) (2025)
- [ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation](https://mlsanity.com/paper/2508.20131/) (2025)
- [Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System](https://mlsanity.com/paper/2507.02170/) (2025)
- [Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models](https://mlsanity.com/paper/2408.05241/) (2024)
- [ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents](https://mlsanity.com/paper/2509.25299/) (2025)
- [AI-Powered Math Tutoring: Platform for Personalized and Adaptive Education](https://mlsanity.com/paper/2507.12484/) (2025)
- [On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study](https://mlsanity.com/paper/2505.11839/) (2025)
- [AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs](https://mlsanity.com/paper/2510.13912/) (2025)
- [When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements](https://mlsanity.com/paper/2502.15153/) (2025)
- [Towards Developing Ethical Reasoners: Integrating Probabilistic Reasoning and Decision-Making for Complex AI Systems](https://mlsanity.com/paper/2502.21250/) (2025)
- [AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation](https://mlsanity.com/paper/2503.11346/) (2025)

## Built on by (most cited first, 5 of 5)

- [Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory](https://mlsanity.com/paper/2604.03588/) (2026)
- [Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation](https://mlsanity.com/paper/2606.10475/) (2026)
- [CHAL: Council of Hierarchical Agentic Language](https://mlsanity.com/paper/2605.12718/) (2026)
- [CAF-Gen: A Multi-Agent System for Enriching Argumentation Structures](https://mlsanity.com/paper/2606.06646/) (2026)
- [Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks](https://mlsanity.com/paper/2609.28673/) (2026)

## Abstract (arXiv)

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.