構建您的個性化研究團隊：一個持續互動科學自動化的多智能體框架

摘要

科學發現的自動化標誌著人工智慧（AI）研究中的一個關鍵里程碑。然而，現有的科學代理系統存在兩個根本性限制：僵化的預設工作流程無法適應中間發現，以及不足的上下文管理阻礙了長期研究。我們提出了freephdlabor，這是一個開源的多代理框架，其特點是完全動態的工作流程由實時代理推理決定，並採用模組化架構，使用戶能夠無縫地進行定制——用戶可以修改、添加或移除代理以滿足特定領域的需求。該框架提供了全面的基礎設施，包括自動上下文壓縮、基於工作區的通信以防止信息退化、跨會話的記憶持久性，以及非阻塞的人類干預機制。這些功能共同將自動化研究從孤立的單次嘗試轉變為持續的研究計劃，這些計劃系統地建立在先前探索的基礎上，並融入人類反饋。通過提供構建可定制的共同科學家系統的架構原則和實際實現，這項工作旨在促進自動化研究在科學領域的更廣泛採用，使從業者能夠部署互動式多代理系統，這些系統自主地進行端到端的研究——從構思到實驗，再到準備發表的文稿。

English

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 freephdlabor, an open-source multiagent framework featuring fully dynamic workflows determined by real-time agent reasoning and a \textit{modular architecture} enabling seamless customization -- users can modify, add, or remove agents to address domain-specific requirements. The framework provides comprehensive infrastructure including automatic context compaction, workspace-based communication to prevent information degradation, memory persistence across sessions, and non-blocking human intervention mechanisms. These features collectively transform automated research from isolated, single-run attempts into 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.

構建您的個性化研究團隊：一個持續互動科學自動化的多智能體框架

Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation

摘要

Support