Saved in:
Bibliographic Details
Main Authors: Zhang, Yingjie, Feng, Chun, Zhu, Weizhang, Sun, Tianshu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17746
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914576135618560
author Zhang, Yingjie
Feng, Chun
Zhu, Weizhang
Sun, Tianshu
author_facet Zhang, Yingjie
Feng, Chun
Zhu, Weizhang
Sun, Tianshu
contents AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and operate in multi-agent arrangements. Understanding their effects therefore requires more than measuring output accuracy; it requires evidence about mechanisms, delegation, feedback, and control. Experiments remain central to this task, but they also face a recursive challenge: we need experiments for agents to study these arrangements, and we may need agents for experiments to help search the expanding space of possible designs. Yet experimental conditions for human-AI and agentic workflows are still largely specified in prose, making them difficult to compare, reuse, or audit. We frame this as a problem of workflow representation, traceability, and governance in AI-enabled knowledge production. We introduce SEED (Structural Encoding for Experimental Discovery), a framework that represents experimental conditions as typed actor-flow graphs. SEED supports three design functions: describing conditions as interaction structures, evaluating structural novelty relative to encoded prior designs, and generating candidate designs under feasibility and governance constraints. We report a lightweight empirical feasibility test that compares graph-blind and SEEDguided generation in a medical-triage design task. In this diagnostic contrast, SEED-guided candidate designs show clearer actor-flow changes, assumptions, and governance checks, supporting the feasibility of the grammar as a design aid. The commentary closes by identifying governance tensions around novelty, replication, validity, diversity of inquiry, and accountability.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17746
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science
Zhang, Yingjie
Feng, Chun
Zhu, Weizhang
Sun, Tianshu
Artificial Intelligence
Human-Computer Interaction
AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and operate in multi-agent arrangements. Understanding their effects therefore requires more than measuring output accuracy; it requires evidence about mechanisms, delegation, feedback, and control. Experiments remain central to this task, but they also face a recursive challenge: we need experiments for agents to study these arrangements, and we may need agents for experiments to help search the expanding space of possible designs. Yet experimental conditions for human-AI and agentic workflows are still largely specified in prose, making them difficult to compare, reuse, or audit. We frame this as a problem of workflow representation, traceability, and governance in AI-enabled knowledge production. We introduce SEED (Structural Encoding for Experimental Discovery), a framework that represents experimental conditions as typed actor-flow graphs. SEED supports three design functions: describing conditions as interaction structures, evaluating structural novelty relative to encoded prior designs, and generating candidate designs under feasibility and governance constraints. We report a lightweight empirical feasibility test that compares graph-blind and SEEDguided generation in a medical-triage design task. In this diagnostic contrast, SEED-guided candidate designs show clearer actor-flow changes, assumptions, and governance checks, supporting the feasibility of the grammar as a design aid. The commentary closes by identifying governance tensions around novelty, replication, validity, diversity of inquiry, and accountability.
title Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2605.17746