Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

TL;DR

This paper reviews the current state, challenges, and future directions of open-domain conversational agents, emphasizing qualities like engagement, continual learning, and safety, while highlighting gaps and community recommendations.

Contribution

It offers a focused overview of progress and open problems in building engaging, safe, and adaptable conversational agents, based on the authors' experiences and insights.

Findings

Progress in continual learning for agents

Identification of key qualities for engaging agents

Open challenges in safety and content generation

Abstract

We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been built so far, and the gaping holes we have not filled yet. We present a biased view, focusing on work done by our own group, while citing related work in each area. In particular, we discuss in detail the properties of continual learning, providing engaging content, and being well-behaved -- and how to measure success in providing them. We end with a discussion of our experience and learnings, and our recommendations to the community.