{"ID":2854100,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15624","arxiv_id":"2510.15624","title":"Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation","abstract":"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.","short_abstract":"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 hinde...","url_abs":"https://arxiv.org/abs/2510.15624","url_pdf":"https://arxiv.org/pdf/2510.15624v1","authors":"[\"Ed Li\",\"Junyu Ren\",\"Xintian Pan\",\"Cat Yan\",\"Chuanhao Li\",\"Dirk Bergemann\",\"Zhuoran Yang\"]","published":"2025-10-17T13:13:32Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.LG\",\"cs.MA\"]","methods":"[\"LoRA\"]","has_code":false}