@inproceedings{qiu-etal-2025-completing,
    title = "Completing A Systematic Review in Hours instead of Months with Interactive {AI} Agents",
    author = "Qiu, Rui  and
      Chen, Shijie  and
      Su, Yu  and
      Yen, Po-Yin  and
      Shen, Han Wei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1523/",
    pages = "31559--31593",
    ISBN = "979-8-89176-251-0",
    abstract = "Systematic reviews (SRs) are vital for evidence-based practice in high stakes disciplines, such as healthcare, but are often impeded by intensive labors and lengthy processes that can take months to complete. Due to the high demand for domain expertise, existing automatic summarization methods fail to accurately identify relevant studies and generate high-quality summaries. To that end, we introduce InsightAgent, a human-centered interactive AI agent powered by large language models that revolutionize this workflow. InsightAgent partitions a large literature corpus based on semantics and employs a multi-agent design for more focused processing of literature, leading to significant improvement in the quality of generated SRs. InsightAgent also provides intuitive visualizations of the corpus and agent trajectories, allowing users to effortlessly monitor the actions of the agent and provide real-time feedback based on their expertise. Our user studies with 9 medical professionals demonstrate that the visualization and interaction mechanisms can effectively improve the quality of synthesized SRs by 27.2{\%}, reaching 79.7{\%} of human-written quality. At the same time, user satisfaction is improved by 34.4{\%}. With InsightAgent, it only takes a clinician about 1.5 hours, rather than months, to complete a high-quality systematic review."
}