Towards Lifelong Dialogue Agents via Timeline-based Memory Management
This work addresses the challenge of long-term human-agent interaction by enabling agents to retain and utilize all past memories, which is incremental as it builds on prior memory management methods but shifts focus from removal to linking.
The paper tackles the problem of lifelong dialogue agents needing to manage large-scale memories without discarding outdated ones, and presents THEANINE, a framework that uses memory timelines based on temporal and cause-effect relations to improve response generation, achieving state-of-the-art performance on benchmarks like PersonaChat and LIGHT with improvements of up to 15% in metrics like BLEU and F1.
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 While prior studies focus on getting rid of outdated memories to improve retrieval quality, we argue that such memories provide rich, important contextual cues for RG (e.g., changes in user behaviors) in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.