Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science

2026-07-14

AI Summary

This work addresses the challenge of inefficient collaboration between multi-role human experts and AI systems in complex scientific research by introducing a novel paradigm termed “networked intelligence.” It frames scientific collaboration as a sparse conditional computation problem, explicitly distinguishing tasks solvable by individual agents from those requiring irreducible, shared contextual understanding. To operationalize this paradigm, we present Mycelium—an active shared workspace that automatically captures and interconnects hypotheses and observations generated by both humans and AI through proactive context graph construction, a multi-user collaborative reasoning architecture, and dynamic knowledge routing. Evaluated in multi-omics biological experiments, the system demonstrates its ability to transform localized analyses into cross-domain mechanistic constraints via contextual routing and effectively guide the design of novel experiments.

Abstract

Most AI-for-science systems focus on scaling a single reasoning process through better models, larger context windows, long-horizon agentic execution, or digital co-scientists working with one principal user. However, challenging scientific problems are rarely solved by one reasoner alone. They are solved by teams whose members bring different priors, experimental backgrounds, tacit knowledge, and domain-trained intuitions. The open problem is therefore not only how to scale models, but how to cultivate networked intelligence: scaling the connections between humans and AI systems so that a result or hypothesis produced in one context reaches another person, agent, instrument, or robot that can act on it. We introduce Mycelium, an active shared workspace that automatically connects researchers and AI agents as a multi-user co-scientist. As human users and agents work, the system captures important observations and hypotheses, tracks how they relate to the team's evolving model, and routes them to the person or agent whose next decision they can inform. We evaluate Mycelium in its first empirical test, a biological multi-omics campaign in which routed shared context turned a local analytical finding into a cross-expert mechanistic constraint and ultimately into an experimental design. We also give networked intelligence a computational account as sparse conditional computation over distributed scientific contexts. This account distinguishes when a scaled standalone agent can match the network from when independent expertise and non-mergeable contexts make the network irreducible.

Problem

• networked intelligence
• human-AI collaboration
• shared context
• team science
• scientific reasoning

Innovation

• networked intelligence
• active shared context graphs
• multi-user co-scientist
• sparse conditional computation
• human-AI team science