Chinese contentarXiv 论文：多智能体筛选中一致性与接受度无法界定召回率
做 AI 审阅、论文初筛或 e-discovery 的团队值得看这篇：它证明多智能体一致不代表正确，接受率只能给 precision，想算 recall 必须抽样审核被拒条目。相比一般的多智能体评估讨论，这篇给出了严格的统计边界，适合搭筛选流水线的工程师和数据质量负责人。
#paper review
5 stories · 1 in 7 days · 1 in 30 days
Stories, products and papers tagged "paper review", newest first.
Nov 10
Oct 11
Sakana AI Multi-Layered Review Catches 73% of Core-Claim Errors
The 73.43% figure matters less than the gap: prior automated reviewers caught under 15% of core-claim errors, so MLR moves claim-level checking from near-useless to partially reliable, while still missing roughly one in four. Conference and journal programme committees weighing AI-assisted triage can use the Contradiction Benchmark as a baseline before trusting any reviewer agent on submissions.
Aug 5
Chinese contentLLM评审与人类同行评审对齐程度如何
让GPT-5.4、Gemini 3.1和Claude 4.6评审300篇ICLR论文，发现它们能区分录用和拒稿，但分不清oral和poster，Gemini给分偏高。用AI审稿前先看看这个。
Jun 12
Chinese contentJohn Schulman 加入 AI 科学分析平台，助力深度论文评审
AI 在科研评审中的落地案例来了——做学术写作或论文评审的团队值得关注，Schulman 的背书意味着这个方向有实质进展。
May 27
Chinese contentE3：自动化论文评审的Issue级回测系统
E3解决了论文评审中遗漏关键技术问题的痛点，做学术评审或论文质量控制的团队可以直接用这套开源工具提升效率，建议点开看看具体实现。