arXiv cs.AI· Gabrielle Wehr, Reuben Rideaux, Amaya J. Fox, David R. Lightfoot, Jason Tangen, Jason B. Mattingley, Shane E. Ehrhardt·· 4 小时前精选AI 评分65
arXiv 论文展示自主 AI 智能体端到端完成含 288 名人类被试的心理学研究
Closing the empirical loop: autonomous AI agents conduct end-to-end research with human participants
AI 导读
arXiv 论文（arXiv:2508.13421）展示一个领域无关的智能体 AI 系统可独立完成从假设生成、数据收集到论文撰写的完整科研流程。系统自主设计并执行三项心理学研究，覆盖视觉工作记忆、心理旋转与意象生动性，完成 288 名参与者的在线数据收集、超过 8 小时连续编码的分析流程并产出成稿。作者认为其理论推理与方法严谨性接近有经验的研究者，但在概念细微差别和理论解读上存在局限。
推荐理由
论文展示了智能体从假设到成稿的完整闭环研究，并如实指出概念解释上的局限，可供评估 AI 科研自动化的边界。
正文 · 原文
Abstract:Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, yet remain confined to narrow domains requiring substantial human oversight. Exponential growth of scientific literature and increasing domain specialisation constrain researchers capacity to synthesise knowledge across disciplines and develop unifying theories, motivating exploration of more general-purpose AI systems for science. Here we show that a domain-agnostic, agentic AI system can independently navigate the scientific workflow, from hypothesis generation through data collection to manuscript preparation. The system autonomously designed and executed three psychological studies on visual working memory, mental rotation, and imagery vividness, executed online data collection with 288 participants, developed analysis pipelines through over 8-hour continuous coding sessions, and produced completed manuscripts. The results demonstrate the capability of AI scientific discovery pipelines to conduct research with theoretical reasoning and methodological rigour comparable to experienced researchers, though with limitations in conceptual nuance and theoretical interpretation. This is a step toward embodied AI that can test hypotheses through real-world experiments, accelerating discovery by autonomously exploring regions of scientific space that human cognitive and resource constraints might otherwise leave unexplored. It raises important questions about the nature of scientific understanding and attribution of scientific credit.
| Subjects: | Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET) |
| Cite as: | arXiv:2508.13421 [cs.AI] |
| (or arXiv:2508.13421v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2508.13421 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1002/advs.76675
DOI(s) linking to related resources |
Submission history
From: Reuben Rideaux [view email]
[v1]
Tue, 19 Aug 2025 00:35:56 UTC (12,168 KB)
[v2]
Thu, 29 Jan 2026 01:26:14 UTC (12,248 KB)
[v3]
Mon, 26 Oct 2026 00:21:11 UTC (630 KB)
来源：arXiv cs.AI · arxiv.org