DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
This addresses the challenge of robust memory management in conversational AI systems, though it appears incremental as it builds on existing persona-centric memory frameworks.
The paper tackles the problem of information loss and fragility in persona-centric memory management for multi-agent systems by proposing DeltaMem, a single-agent system that uses reinforcement learning with a novel memory-based reward. The results show that DeltaMem outperforms product-level baselines on benchmarks like LoCoMo, HaluMem, and PersonaMem.
Recent advances in persona-centric memory have revealed the powerful capability of multi-agent systems in managing persona memory, especially in conversational scenarios. However, these complex frameworks often suffer from information loss and are fragile across varying scenarios, resulting in suboptimal performance. In this paper, we propose DeltaMem, an agentic memory management system that formulates persona-centric memory management as an end-to-end task within a single-agent setting. To further improve the performance of our agentic memory manager, we draw inspiration from the evolution of human memory and synthesize a user-assistant dialogue dataset along with corresponding operation-level memory updating labels. Building on this, we introduce a novel Memory-based Levenshtein Distance to formalize the memory updating reward, and propose a tailored reinforcement learning framework to further enhance the management capabilities of DeltaMem. Extensive experiments show that both training-free and RL-trained DeltaMem outperform all product-level baselines across diverse long-term memory benchmarks, including LoCoMo, HaluMem, and PersonaMem.