Stephanie2: Thinking, Waiting, and Making Decisions Like Humans in Step-by-Step AI Social Chat
Hao Yang, Hongyuan Lu, Dingkang Yang, Wenliang Yang, Peng Sun, Xiaochuan Zhang, Jun Xiao, Kefan He, Wai Lam, Yang Liu, Xinhua Zeng

TL;DR
Stephanie2 is a novel AI social chat system that improves message pacing and naturalness by actively deciding when to send or wait, closely mimicking human conversation flow.
Contribution
It introduces active waiting and message-pace adaptation in step-by-step AI chat, enhancing naturalness and engagement over previous models.
Findings
Outperforms Stephanie1 in naturalness and engagement
Achieves higher pass rate on role identification Turing test
Models latency as thinking and typing time for realistic pacing
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSocial Robot Interaction and HRI · AI in Service Interactions · Speech and dialogue systems
