摘要：科学出版物数量的快速增长给同行评审带来了压力，尤其是在机器学习领域，引发了人们对评审质量下降和评审人工作负担加重的担忧。大语言模型（LLM）已被提议用作自动化评审助手，但对这类系统的评估主要集中在人类撰写评审意见的模仿程度上，而非其对同行评审核心功能的支持。本文提出一种以验证为中心的 LLM 辅助同行评审视角，强调错误检测是一项关键且资源密集的任务。我们提出一个可扩展的基准，通过向会议论文中合成插入错误，评估评审系统识别逻辑矛盾的能力，从而形成明确无歧义的评估目标，并支持系统性比较。我们还提出了多层评审（Multi-Layered Review，MLR）框架，在生成评审意见之前优先深入理解论文，使其更贴近人类评审实践，同时提高 token 使用效率。在各项评估中，我们的方法与人类评审评分高度一致，在错误检测方面表现出色，并提供了关于评审关注点的互补视角。这些改进既可归因于底层 LLM 的选择，也可归因于系统设计。同时，我们证实了系统仍持续存在易受对抗性操纵的弱点，凸显了自动评审系统稳健性的必要性。研究结果强调，应通过严格、以错误为重点的评估，引导基于 LLM 的工具在同行评审及其他关键科学工作流程中得到负责任的部署。

Abstract:The rapid growth of scientific publishing has strained peer review, particularly in machine learning, raising concerns about declining review quality and increasing reviewer workload. Large language models (LLMs) have been proposed as automated review assistants, yet their evaluation has focused largely on imitating human-written reviews rather than supporting the core functions of peer review. Here, we introduce a verification-centric perspective on LLM-assisted peer review, emphasizing error detection as a critical and resource-intensive task. We present a scalable benchmark that evaluates review systems' ability to identify logical contradictions, constructed through synthetic insertion of errors into conference papers, yielding unambiguous evaluation targets and enabling systematic comparison. We further propose a Multi-Layered Review (MLR) framework that prioritizes detailed manuscript comprehension before review generation, aligning more closely with human reviewing practices while improving token efficiency. Across evaluations, our approach demonstrates strong alignment with human review scores, achieves high error detection performance, and provides complementary perspectives on reviewer focus. These improvements can be attributed to both the choice of the underlying LLM and the design of our system. At the same time, we corroborate persistent vulnerabilities to adversarial manipulation, underscoring the need for robustness in automated review systems. Our findings highlight the importance of rigorous, error-focused evaluation to guide responsible deployment of LLM-based tools in peer review and other critical scientific workflows.