Labtune creates flexible AI lab setups to test teamwork styles
Labtune: Treating Lab Organization and Information Sharing as Experimental Variables in LLM-Agent Discovery
Multiagent Systems
Summary
Organizing research teams can either help share ideas or cause everyone to think the same way, which is a problem. The paper presents Labtune, a system where different ways to set up and share information in AI-led labs can be easily changed and tested. By letting users pick how labs and info flow are arranged and controlling communication, Labtune helps explore which setups might work best. The authors do not claim any one setup is best, but instead want to create a way to study these differences fairly.
What this means in practice
- •For ai development teams: Test different team arrangements and sharing rules among autonomous AI agents to improve research coordination within the same budget.
- •For software project managers: Design modular experimental workflows to compare collaboration methods and communication limits among distributed software teams.
A position paper. It proposes an approach and reports no results.
Authors
Goran Mitevski
Abstract
De-siloing can create groupthink; silos can prevent knowledge sharing and reduce research efficiency. The same tension appears in research systems built with large language model (LLM) agents, yet their organization is usually fixed by design. I propose treating laboratory structure and information sharing as experimental variables. I introduce Labtune, an open framework for bounded research workflows with user-selected laboratory organization, communication policy, model configuration and budget. Users can choose among six editable designs, from multidisciplinary silos and transdisciplinary teams to co-leaders, hub-and-spoke structures, flat co-labs and a single scientist. Information sharing can independently vary from none to high detail, with an optional channel for conditional abstractions called wisdom. Sharing is enforced by the controller at phase barriers rather than through unrestricted agent chat, while delegation does not create additional budget or permissions. Development evidence is separated from protected confirmation, and an optional multi-lab layer allows laboratories with different structures to exchange filtered information. Labtune is an idea and system-description paper, not a benchmark result. Its contribution is to make laboratory organization and information sharing configurable and measurable under matched budgets. I do not claim that one design or level of sharing is best; the aim is to create a concrete experimental space in which those differences can be tested.