arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.22648cs.HCcs.AI
收藏

AwesomeLit: 向基于代理支持的文献研究进行假设生成

AwesomeLit: Towards Hypothesis Generation with Agent-Supported Literature Research

School of Computer Science, University of Nottingham, UK(诺丁汉大学计算机科学学院);School of Intelligence Science and Technology, Peking University, China(北京大学智能科学与技术学院)

Zefei Xie, Yuhan Guo, Kai Xu

AI总结:

本文提出AwesomeLit系统,通过可视化工具帮助用户探索未知领域,识别研究方向并提升信心。

摘要:

文献研究有不同的目标,从理解不熟悉的话题到为下一个研究项目生成假设。根据用户对主题的熟悉程度,文献研究的性质也有所不同。对于经验不足的研究人员,识别现有文献中的空白并生成可行的假设是至关重要的,但具有挑战性。尽管可以使用通用的“深入研究”工具,但它们并非为此用途而设计,因此往往不有效。此外,大型语言模型(LLMs)的“黑箱”性质和幻觉常常导致不信任。在本文中,我们介绍了一个人-代理协作的可视化系统AwesomeLit,以解决这一需求。它具有几个新颖的功能:透明的用户可控制的代理工作流;动态生成的查询探索树,可视化探索路径和来源;以及语义相似性视图,描绘论文之间的关系。它使用户能够从一般意图过渡到详细研究主题。最后,一项涉及几位早期研究人员的定性研究显示,AwesomeLit在帮助用户探索不熟悉的话题、识别有前途的研究方向以及提高对研究结果的信心方面是有效的。

英文摘要:

There are different goals for literature research, from understanding an unfamiliar topic to generate hypothesis for the next research project. The nature of literature research also varies according to user's familiarity level of the topic. For inexperienced researchers, identifying gaps in the existing literature and generating feasible hypothesis are crucial but challenging. While general ``deep research'' tools can be used, they are not designed for such use case, thus often not effective. In addition, the ``black box" nature and hallucination of Large Language Models (LLMs) often lead to distrust. In this paper, we introduce a human-agent collaborative visualization system AwesomeLit to address this need. It has several novel features: a transparent user-steerable agentic workflow; a dynamically generated query exploring tree, visualizing the exploration path and provenance; and a semantic similarity view, depicting the relationships between papers. It enables users to transition from general intentions to detailed research topics. Finally, a qualitative study involving several early researchers showed that AwesomeLit is effective in helping users explore unfamiliar topics, identify promising research directions, and improve confidence in research results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑