arXiv AI
Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 13
Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
arXiv:2607. 09195v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery.
arXiv AI
Sep 1
Science sandboxes measure the scientific capability of AI agents
arXiv:2608.30165v1 Announce Type: cross Abstract: Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to desig...
arXiv AI
Jun 16
Towards End-to-End Automation of AI Research
arXiv:2606. 15497v1 Announce Type: new Abstract: The automation of science is a long-standing ambition in the field of AI.
arXiv AI
Jul 21
From Overload to Insights: How AI Agents Can Support Scientists in Analyzing Complex Data
arXiv:2607. 16845v1 Announce Type: new Abstract: Scientists at European XFEL conduct experiments that generate very large and complex datasets.
arXiv AI
Jun 11
Preregistration for Experiments with AI Agents
arXiv:2606. 11217v1 Announce Type: cross Abstract: The proliferation of large language models (LLMs) and autonomous AI agents has given rise to a rapidly growing methodological paradigm: "in silico" behavioral experiments.
arXiv AI
Sep 1
HumanStudy-Bench: Towards AI Agent Design for Participant Simulation
arXiv:2602.00685v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable an...