A Vision for Auto Research with LLM Agents

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.

@article{liu2025_2504.18765,
  title={ A Vision for Auto Research with LLM Agents },
  author={ Chengwei Liu and Chong Wang and Jiayue Cao and Jingquan Ge and Kun Wang and Lvye Zhang and Ming-Ming Cheng and Penghai Zhao and Tianlin Li and Xiaojun Jia and Xiang Li and Xinfeng Li and Yang Liu and Yebo Feng and Yihao Huang and Yijia Xu and Yuqiang Sun and Zhenhong Zhou and Zhengzi Xu },
  journal={arXiv preprint arXiv:2504.18765},
  year={ 2025 }
}