Instant-messaging human social chat typically progresses through a sequence of short messages. Existing step-by-step AI chatting systems typically split a one-shot generation into multiple messages and send them sequentially, but they lack an active waiting mechanism and exhibit unnatural message pacing. In order to address these issues, we propose Stephanie2, a novel next-generation step-wise decision-making dialogue agent. With active waiting and message-pace adaptation, Stephanie2 explicitly decides at each step whether to send or wait, and models latency as the sum of thinking time and typing time to achieve more natural pacing. We further introduce a time-window-based dual-agent dialogue system to generate pseudo dialogue histories for human and automatic evaluations. Experiments show that Stephanie2 clearly outperforms Stephanie1 on metrics such as naturalness and engagement, and achieves a higher pass rate on human evaluation with the role identification Turing test.
@article{arxiv.2601.05657,
title = {Stephanie2: Thinking, Waiting, and Making Decisions Like Humans in Step-by-Step AI Social Chat},
author = {Hao Yang and Hongyuan Lu and Dingkang Yang and Wenliang Yang and Peng Sun and Xiaochuan Zhang and Jun Xiao and Kefan He and Wai Lam and Yang Liu and Xinhua Zeng},
journal= {arXiv preprint arXiv:2601.05657},
year = {2026}
}