Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents

ICLR 2026 Conference Submission20843 Authors

Keywords: agentic discovery, autonomous science

Abstract: Large-scale scientific datasets—spanning health biobanks, cell atlases, Earth reanalyses, and more—create opportunities for exploratory discovery unconstrained by specific research questions. We term this process $\textit{hypothesis hunting}$: the cumulative search for insight through sustained exploration across vast and complex hypothesis spaces. To support it, we introduce $\texttt{AScience}$, a framework modeling discovery as the interaction of agents, networks, and evaluation norms, and implement it as $\texttt{ASCollab}$, a distributed system of LLM-based research agents with heterogeneous behaviors. These agents self-organize into evolving networks, continually producing and peer-reviewing findings under shared standards of evaluation. Experiments show that such social dynamics enable the accumulation of expert-rated results along the diversity–quality–novelty frontier, including rediscoveries of established biomarkers, extensions of known pathways, and proposals of new therapeutic targets. While wet-lab validation remains indispensable, our experiments on cancer cohorts demonstrate that socially structured, agentic networks can sustain exploratory hypothesis hunting at scale.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 20843