自动研究系统完成流程不等于科学可信，需外部知识控制。
Workflow Closure Is Not Scientific Closure in Auto-Research Systems
- 用外部知识控制替代完全自主，确保研究可信性。
- 发现三大失效模式：目标、验证和接受的塌陷。
- 适合关注AI科研伦理与系统设计的研究者阅读。
本文指出，自动研究系统中流程闭环不等于科学闭环。当前系统虽能内化完成从构思到实验、写作与自评的研究循环，但这一成就并不赋予其成果科学可信性。可信的自动研究不应追求完全自主，而应实现自主执行下的非自主认知控制。基于对100余篇论文及仓库的调研，以及对21个代表性系统的结构化审计，我们诊断出一种反复出现且结构性关联的失败模式：目标塌陷（单一代理目标取代多目标科学目标）、验证塌陷（内部自评取代独立验证）、接受塌陷（基准分数或发表形态产物取代领域级批判、复用与整合机制）。这些塌陷并非自主性的固有局限，而是可修正的设计选择。为此，我们从目标信号、验证机制和输出路径三方面提出潜在修复方案，以推动学界讨论。
原文摘要 · Abstract (English)
This paper argues that workflow closure is not scientific closure in auto-research systems. Current systems can increasingly complete research-like loops internally, moving from idea generation to experiment execution, writing, and self-evaluation. That achievement is real, but it does not by itself give the resulting outputs scientific standing. We argue that trustworthy auto-research should not aim for autonomous self-sufficiency, but should aim for autonomous execution under non-autonomous epistemic control. Based on a survey of more than 100 recent papers and repositories in this rapidly emerging area, together with a structured audit of 21 representative systems, we diagnose a recurring and structurally connected failure pattern: objective collapse, in which single-proxy targets replace multi-objective scientific aims; validation collapse, in which internal self-evaluation replaces independent validation; and acceptance collapse, in which benchmark scores or publication-shaped artifacts replace mechanisms for domain-level critique, reuse, and integration. These collapses are not inherent limits of autonomy but correctable design choices. Accordingly, we outline potential remedies across objective signal, validation, and output pathway to spark community discussion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。