Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation
This work addresses the problem of automating scientific discovery for researchers by providing a customizable framework, though it appears incremental as it builds on existing multiagent concepts with specific enhancements.
The paper tackles the limitations of existing agentic systems for science, which are rigid and lack context management, by introducing an open-source multiagent framework that enables fully dynamic workflows and modular customization, resulting in a system that supports continual research programs with human feedback.
The automation of scientific discovery represents a critical milestone in Artificial Intelligence (AI) research. However, existing agentic systems for science suffer from two fundamental limitations: rigid, pre-programmed workflows that cannot adapt to intermediate findings, and inadequate context management that hinders long-horizon research. We present \texttt{freephdlabor}, an open-source multiagent framework featuring \textit{fully dynamic workflows} determined by real-time agent reasoning and a \coloremph{\textit{modular architecture}} enabling seamless customization -- users can modify, add, or remove agents to address domain-specific requirements. The framework provides comprehensive infrastructure including \textit{automatic context compaction}, \textit{workspace-based communication} to prevent information degradation, \textit{memory persistence} across sessions, and \textit{non-blocking human intervention} mechanisms. These features collectively transform automated research from isolated, single-run attempts into \textit{continual research programs} that build systematically on prior explorations and incorporate human feedback. By providing both the architectural principles and practical implementation for building customizable co-scientist systems, this work aims to facilitate broader adoption of automated research across scientific domains, enabling practitioners to deploy interactive multiagent systems that autonomously conduct end-to-end research -- from ideation through experimentation to publication-ready manuscripts.