Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration

2026-06-29

AI Summary

This work addresses the lack of infrastructure supporting open, traceable, and multi-stakeholder collaboration in current autonomous scientific agents, which hinders effective coordination of resources and tasks under uncertainty. The paper proposes the first Web-scale infrastructure framework for scientific collaboration, reframing research as an open, auditable, traceable, and resource-aware multi-stage collaborative process. Built upon a project–agent–resource object model and a four-layer collaboration protocol—spanning research applications, digital collaboration, physical substrates, and the physical world—the framework integrates pluggable modules and trust mechanisms to shift the paradigm from code-centric execution to research-oriented collaboration. Demonstrated through a paper-generation case study, the system successfully constructs a cross-stage collaborative network that is traceable, reviewable, attributable, and cumulative, laying the foundation for open science; the system is now operational.

Abstract

Existing autonomous research agents can support parts of the research process, but most systems still treat research as either an isolated assistant task or a closed workflow. Therefore, autonomous science needs a collaboration infrastructure that coordinates projects, agents, and digital and physical resources. We identify this as a shift from code-centered execution loops to research-oriented collaboration processes, where questions, evidence, participants, and resources must be coordinated under uncertainty. In this framing, an agent may be an AI system, a human researcher, a team, a laboratory, or an organization-backed participant. To this end, we present Clarus, a collaboration infrastructure for coordinating autonomous research agents toward web-scale scientific collaboration. Clarus reformulates research as an open, auditable, attributable, and resource-aware multi-phase collaboration process. It defines a minimal project-agent-resource object model and organizes scientific collaboration through four layers including Research Application, Digital Collaboration, Physical Substrate, and Physical World. Core modules are implemented as pluggable mechanisms, allowing Clarus to adapt to task risk, collaboration structure, and resource constraints. Through a controlled paper-generation case study, we show that Clarus can organize a research goal into a traceable, reviewable, attributable, and accumulative collaboration network across phases, tasks, and participants. Together, the object model, collaboration protocol, trust mechanisms, and prototype validation provide an initial foundation for open research networks. Clarus is now available at clarus.holosai.io.

Problem

• autonomous research agents
• scientific collaboration
• collaboration infrastructure
• web-scale research
• resource coordination

Innovation

• autonomous research agents
• scientific collaboration
• collaboration infrastructure
• resource-aware coordination
• attributable research