mlsanityData to 14 Oct 2026

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

arXiv 2509.13356 ↗First posted 14 Sep 2025cs.CY cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

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.

Builds on

22 of 81 references.

References · 22

  1. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  3. 2016Concrete Problems in AI Safetycited by 1,642
  4. 2020Aligning AI With Shared Human Valuescited by 723
  5. 2020Artificial Intelligence, Values and Alignmentcited by 448
  6. 2018AI safety via debatecited by 400
  7. 2024Alignment faking in large language modelscited by 360
  8. 2023AI Alignment: A Comprehensive Surveycited by 263
  9. 2024Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessmentcited by 126
  10. 2016Research Priorities for Robust and Beneficial Artificial Intelligencecited by 74
  11. 2024Beyond Preferences in AI Alignmentcited by 49
  12. 2024AI-AI Bias: large language models favor communications generated by large language modelscited by 26
10 more
  1. 2025LLM Ethics Benchmark: A Three-Dimensional Assessment System for Evaluating Moral Reasoning in Large Language Modelscited by 21
  2. 2024AI Governance and Accountability: An Analysis of Anthropic's Claudecited by 14
  3. 2023Generating Valid and Natural Adversarial Examples with Large Language Modelscited by 12
  4. 2025Religious Bias Landscape in Language and Text-to-Image Models: Analysis, Detection, and Debiasing Strategiescited by 9
  5. 2022A Principles-based Ethics Assurance Argument Pattern for AI and Autonomous Systemscited by 6
  6. 2024Beyond Labels: Aligning Large Language Models with Human-like Reasoningcited by 6
  7. 2025Auditing the Ethical Logic of Generative AI Modelscited by 5
  8. 2025Energentic Intelligence: From Self-Sustaining Systems to Enduring Artificial Lifecited by 3
  9. 2015Reciprocal Altruism-based Cooperation in a Social Network Gamecited by 1
  10. 2019Augmented Utilitarianism for AGI Safetycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MoralityGym: A Benchmark for Evaluating Hierarchical Moral Alignment in Sequential Decision-Making Agents
  2. 2023Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto
  3. 2026Beyond Binary Moral Judgment: Modeling Ethical Pluralism in AI
  4. 2026Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment
  5. 2026Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment
  6. 2025PRISM: Perspective Reasoning for Integrated Synthesis and Mediation as a Multi-Perspective Framework for AI Alignment
  7. 2024Informed AI Regulation: Comparing the Ethical Frameworks of Leading LLM Chatbots Using an Ethics-Based Audit to Assess Moral Reasoning and Normative Values
  8. 2025Normative Conflicts and Shallow AI Alignment