Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration
2026-06-29 • Artificial Intelligence
Artificial IntelligenceComputers and SocietyMultiagent Systems
AI summaryⓘ
The authors introduce Clarus, a system designed to help different research agents like AI, humans, and labs work together more smoothly on large scientific projects. Unlike previous tools that handle isolated tasks or closed workflows, Clarus supports open and coordinated collaboration across various resources and participants. Their approach breaks research into clear phases and keeps track of everything to ensure transparency and proper credit. They tested Clarus by coordinating a paper-writing project, showing it can manage complex collaborations effectively. This work lays groundwork for bigger networks of open, shared scientific research.
autonomous research agentscollaboration infrastructureresearch workflowsproject-agent-resource modelscientific collaborationopen research networkstrust mechanismsmulti-phase collaborationdigital collaboration
Authors
Zihan Guo, Zeyi Chen, Zhiyu Chen, Zicai Cui, Shuai Shao, Bo Huang, Zhi Han, Yuanyi Song, Yuan Yuan, Chenxi Zeng, Xiaohang Nie, Zhengxi Yu, Hanwen Zhu, Junwei Liao, Ming Zhou, Yang Li, Yuanjian Zhou, Weinan Zhang
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.