Towards Lifelong Dialogue Agents via Timeline-based Memory Management

TL;DR

This paper introduces THEANINE, a framework for lifelong dialogue agents that manages memories through timeline-based linking, enhancing response generation by utilizing rich contextual cues from long-term conversations.

Contribution

It proposes a novel memory management approach that links memories over time and causality, enabling better long-term context utilization in dialogue agents.

Findings

THEANINE improves response relevance by leveraging linked memories.

TeaFarm provides a counterfactual evaluation scheme for memory integration.

The framework supports large-scale memory management without discarding outdated information.

Abstract

To achieve lifelong human-agent interaction, dialogue agents need to constantly memorize perceived information and properly retrieve it for response generation (RG). While prior studies focus on getting rid of outdated memories to improve retrieval quality, we argue that such memories provide rich, important contextual cues for RG (e.g., changes in user behaviors) in long-term conversations. We present THEANINE, a framework for LLM-based lifelong dialogue agents. THEANINE discards memory removal and manages large-scale memories by linking them based on their temporal and cause-effect relation. Enabled by this linking structure, THEANINE augments RG with memory timelines - series of memories representing the evolution or causality of relevant past events. Along with THEANINE, we introduce TeaFarm, a counterfactual-driven evaluation scheme, addressing the limitation of G-Eval and human efforts when assessing agent performance in integrating past memories into RG. A supplementary video for THEANINE and data for TeaFarm are at https://huggingface.co/spaces/ResearcherScholar/Theanine.