Proactive Conversational Agents with Inner Thoughts

要旨

One of the long-standing aspirations in conversational AI is to allow them to autonomously take initiatives in conversations, i.e. being proactive. This is especially challenging for multi-party conversations. Prior NLP research focused mainly on predicting the next speaker from contexts like preceding conversations. In this paper, we demonstrate the limitations of such methods and rethink what it means for AI to be proactive in multi-party, human-AI conversations.We propose that just like humans, rather than merely reacting to turn-taking cues, a proactive AI formulates its own inner thoughts during a conversation, and seeks the right moment to contribute. Through a formative study with 24 participants and inspiration from linguistics and cognitive psychology, we introduce the Inner Thoughts framework. Our framework equips AI with a continuous, covert train of thoughts in parallel to the overt communication process, which enables it to proactively engage by modeling its intrinsic motivation to express these thoughts. We instantiated this framework into two real-time systems: an AI playground web app and a chatbot. Through a technical evaluation and user studies with human participants, our framework significantly surpasses existing baselines on aspects like anthropomorphism, coherence, intelligence, and turn-taking appropriateness.

著者
Xingyu Bruce. Liu
UCLA, Los Angeles, California, United States
Shitao Fang
The University of Tokyo, Tokyo, Japan
Weiyan Shi
Northeastern University, Boston, Massachusetts, United States
Chien-Sheng Wu
Salesforce AI, Palo Alto, California, United States
Takeo Igarashi
The University of Tokyo, Tokyo, Japan
Xiang 'Anthony' Chen
UCLA, Los Angeles, California, United States
DOI

10.1145/3706598.3713760

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713760

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: Conversations with AI

G414+G415
7 件の発表
2025-04-29 23:10:00
2025-04-30 00:40:00
日本語まとめ
読み込み中…