MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaboration
This work addresses the challenge of fostering long-term user-agent collaboration, though it is incremental in building on existing memory and preference-learning methods.
The paper tackles the problem of conversational agents adapting to user preferences over multiple sessions to improve collaboration quality, and shows that equipping agents with a memory designed for learning preferences increases task success rates, efficiency, and user experience.
As conversational agents accumulate experience collaborating with users, adapting to user preferences is essential for fostering long-term relationships and improving collaboration quality over time. We introduce MultiSessionCollab, a benchmark that evaluates how well agents can learn user preferences and leverage them to improve collaboration quality throughout multiple sessions. To develop agents that succeed in this setting, we present long-term collaborative agents equipped with a memory that is specifically designed to learn user preferences across sessions and improve interactions. Moreover, we demonstrate that learning signals can be derived from user simulator behavior in MultiSessionCollab to train agents to generate more comprehensive reflections and update their memory more effectively. Extensive experiments show that equipping agents with our memory improves collaboration over time, yielding higher task success rates, more efficient interactions, and reduced user effort. Finally, we conduct a human user study that demonstrates that memory helps improve user experience in real-world settings.