SEED：面向 AI 实验科学的设计语法（设计语法框架）
Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science
AI 导读
arXiv 概念性评论文章提出 SEED（Structural Encoding for Experimental Discovery），一种将实验条件表示为带类型的 actor-flow 图的语法，用于把公开文献中的实验设计组织成统一表示的共享库。
正文 · 原文
Abstract:Human-AI experiments vary who receives information, who can act, and who holds decision authority. Precise descriptions of individual studies do not by themselves provide a common language for comparing these arrangements. This conceptual commentary proposes SEED (Structural Encoding for Experimental Discovery), a grammar that represents each experimental condition as a typed actor-flow graph. Its purpose is to organize publicly documented studies into a shared library of consistently represented conditions. Human researchers and AI systems can use this common reference to understand prior arrangements and propose extensions for new research questions. The grammar distinguishes structural changes from attribute variation; the scientific value of a proposed change requires substantive argument and evidence. Computational illustrations demonstrate how SEED can support design comparison and AI-assisted development of candidate experimental conditions. We discuss implications for future replication and provenance work, including under restricted data access, and risks of selective search. We call for community agreement on the grammar and coordinated construction and maintenance of the library.
| Subjects: | Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2605.17746 [cs.AI] |
| (or arXiv:2605.17746v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.17746 arXiv-issued DOI via DataCite |
Submission history
From: Yingjie Zhang [view email]
[v1]
Mon, 18 May 2026 01:59:21 UTC (93 KB)
[v2]
Sun, 25 Oct 2026 09:38:50 UTC (81 KB)
来源：arXiv cs.AI · arxiv.org