Mirror: A Multi-Agent System for AI-Assisted Ethics Review

2026-02-09

AI Summary

Current ethical review systems struggle to address structural ethical risks in large-scale, interdisciplinary research due to insufficient capacity, inconsistent standards, and privacy constraints. This work proposes Mirror, a multi-agent framework that integrates normative understanding, an executable rule repository, and a multi-role collaborative deliberation mechanism to support both rapid compliance checks and in-depth committee-like evaluations. Leveraging a newly constructed domain-specific ethical QA dataset, EthicsQA, the authors fine-tune a specialized language model, EthicsLLM, and integrate it with a rule engine and a structured ethical dimension assessment framework. Experimental results demonstrate that the proposed approach significantly outperforms general-purpose large language models in evaluation quality, consistency, and domain expertise, making it suitable for projects ranging from minimal-risk studies to complex scientific endeavors.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Multiagent Systems: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Ethics review is a foundational mechanism of modern research governance, yet contemporary systems face increasing strain as ethical risks arise as structural consequences of large-scale, interdisciplinary scientific practice. The demand for consistent and defensible decisions under heterogeneous risk profiles exposes limitations in institutional review capacity rather than in the legitimacy of ethics oversight. Recent advances in large language models (LLMs) offer new opportunities to support ethics review, but their direct application remains limited by insufficient ethical reasoning capability, weak integration with regulatory structures, and strict privacy constraints on authentic review materials. In this work, we introduce Mirror, an agentic framework for AI-assisted ethical review that integrates ethical reasoning, structured rule interpretation, and multi-agent deliberation within a unified architecture. At its core is EthicsLLM, a foundational model fine-tuned on EthicsQA, a specialized dataset of 41K question-chain-of-thought-answer triples distilled from authoritative ethics and regulatory corpora. EthicsLLM provides detailed normative and regulatory understanding, enabling Mirror to operate in two complementary modes. Mirror-ER (expedited Review) automates expedited review through an executable rule base that supports efficient and transparent compliance checks for minimal-risk studies. Mirror-CR (Committee Review) simulates full-board deliberation through coordinated interactions among expert agents, an ethics secretary agent, and a principal investigator agent, producing structured, committee-level assessments across ten ethical dimensions. Empirical evaluations demonstrate that Mirror significantly improves the quality, consistency, and professionalism of ethics assessments compared with strong generalist LLMs.

Problem

• ethics review
• large-scale scientific practice
• institutional review capacity
• ethical risks
• regulatory compliance

Innovation

• Multi-agent system
• Ethics review
• Large language models
• Ethical reasoning
• Rule-based compliance