arXiv:2504.18765cs.AI2025-04被引 19

用AI代理自动完成科研全流程,提升效率与可扩展性。

A Vision for Auto Research with LLM Agents

  • 构建多智能体协作框架,分工处理文献、实验、写作等环节
  • 初步验证了全链条自动化科研的可行性与潜力
  • 适合希望加速研究流程的学者和科研团队

本文提出基于智能体的自动化科研(Agent-Based Auto Research),一种结构化的多智能体框架,旨在自动化、协调并优化科学研究所涉及的全生命周期。该系统利用大语言模型(LLMs)能力与模块化智能体协作,覆盖从文献综述、创意生成、方法设计、实验执行、论文撰写、同行评审回复到成果传播等主要研究阶段。通过解决工作流碎片化、方法学能力不均和认知过载等问题,该框架为科学研究提供了一种系统化且可扩展的新范式。初步探索表明,自动化科研具备可行性,是未来自迭代、由AI驱动的研究过程的重要方向。

原文摘要 · Abstract (English)

This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Leveraging the capabilities of large language models (LLMs) and modular agent collaboration, the system spans all major research phases, including literature review, ideation, methodology planning, experimentation, paper writing, peer review response, and dissemination. By addressing issues such as fragmented workflows, uneven methodological expertise, and cognitive overload, the framework offers a systematic and scalable approach to scientific inquiry. Preliminary explorations demonstrate the feasibility and potential of Auto Research as a promising paradigm for self-improving, AI-driven research processes.

自动化科研智能体LLM

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。