Reproduce “A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yang Deng, Wenqiang Lei, Wai Lam, Tat-Seng Chua

This paper presents the first comprehensive survey of proactive dialogue systems, defining conversational agent proactivity as the capability to take initiative and anticipate impacts rather than merely responding. It systematically categorizes existing research, highlights critical challenges, and outlines future directions for developing more intelligent, human-like conversational AI agents.

Key insights

  • Proactivity is essential for elevating user engagement, enhancing service efficiency, and managing sophisticated tasks, representing a crucial step towards developing strong AI with autonomy and human-like consciousness.
  • Proactive capabilities are emerging across diverse dialogue types, highlighting an interdisciplinary need to integrate insights from psychology, sociology, and human-computer interaction.
  • Significant challenges remain, including data scarcity for complex proactive interactions, the inherent complexity and cost of evaluating proactivity, and the need for robust, multi-disciplinary evaluation protocols.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.