MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaboration

TL;DR

MultiSessionCollab introduces a benchmark and memory-augmented agents that learn user preferences over multiple sessions, enhancing long-term collaboration quality and user experience.

Contribution

The paper presents a new benchmark for long-term collaborative agents and proposes memory-based agents that effectively learn and utilize user preferences across sessions.

Findings

Memory-equipped agents outperform baselines in success rates

Learning signals from user behavior improve memory updates

Memory enhances user experience in real-world interactions

Abstract

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.