# CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AI

arXiv: https://arxiv.org/abs/2509.13356 · HTML: https://mlsanity.com/paper/2509.13356/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 81 references that are in the map.
- First posted on arXiv 14 Sep 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 22 of 22)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://mlsanity.com/paper/2402.14016/) (2024)
- [Research Priorities for Robust and Beneficial Artificial Intelligence](https://mlsanity.com/paper/1602.03506/) (2016)
- [Beyond Preferences in AI Alignment](https://mlsanity.com/paper/2408.16984/) (2024)
- [AI-AI Bias: large language models favor communications generated by large language models](https://mlsanity.com/paper/2407.12856/) (2024)
- [LLM Ethics Benchmark: A Three-Dimensional Assessment System for Evaluating Moral Reasoning in Large Language Models](https://mlsanity.com/paper/2505.00853/) (2025)
- [AI Governance and Accountability: An Analysis of Anthropic's Claude](https://mlsanity.com/paper/2407.01557/) (2024)
- [Generating Valid and Natural Adversarial Examples with Large Language Models](https://mlsanity.com/paper/2311.11861/) (2023)
- [Religious Bias Landscape in Language and Text-to-Image Models: Analysis, Detection, and Debiasing Strategies](https://mlsanity.com/paper/2501.08441/) (2025)
- [A Principles-based Ethics Assurance Argument Pattern for AI and Autonomous Systems](https://mlsanity.com/paper/2203.15370/) (2022)
- [Beyond Labels: Aligning Large Language Models with Human-like Reasoning](https://mlsanity.com/paper/2408.11879/) (2024)
- [Auditing the Ethical Logic of Generative AI Models](https://mlsanity.com/paper/2504.17544/) (2025)
- [Energentic Intelligence: From Self-Sustaining Systems to Enduring Artificial Life](https://mlsanity.com/paper/2506.04916/) (2025)
- [Reciprocal Altruism-based Cooperation in a Social Network Game](https://mlsanity.com/paper/1510.06197/) (2015)
- [Augmented Utilitarianism for AGI Safety](https://mlsanity.com/paper/1904.01540/) (2019)

## Abstract (arXiv)

The challenge of aligning artificial intelligence (AI) with human values persists due to the abstract and often conflicting nature of moral principles and the opacity of existing approaches. This paper introduces CogniAlign, a multi-agent deliberation framework based on naturalistic moral realism, that grounds moral reasoning in survivability, defined across individual and collective dimensions, and operationalizes it through structured deliberations among discipline-specific scientist agents. Each agent, representing neuroscience, psychology, sociology, and evolutionary biology, provides arguments and rebuttals that are synthesized by an arbiter into transparent and empirically anchored judgments. As a proof-of-concept study, we evaluate CogniAlign on classic and novel moral questions and compare its outputs against GPT-4o using a five-part ethical audit framework with the help of three experts. Results show that CogniAlign consistently outperforms the baseline across more than sixty moral questions, with average performance gains of 12.2 points in analytic quality, 31.2 points in decisiveness, and 15 points in depth of explanation. In the Heinz dilemma, for example, CogniAlign achieved an overall score of 79 compared to GPT-4o's 65.8, demonstrating a decisive advantage in handling moral reasoning. Through transparent and structured reasoning, CogniAlign demonstrates the feasibility of an auditable approach to AI alignment, though certain challenges still remain.