MemOrb: A Plug-and-Play Verbal-Reinforcement Memory Layer for E-Commerce Customer Service
This addresses reliability issues for e-commerce customer service agents, offering a plug-and-play solution that is incremental as it builds on existing frozen LLM agents without fine-tuning.
The paper tackled the problem of LLM-based agents in customer service forgetting across sessions and repeating errors, proposing MemOrb, a plug-and-play memory layer that improved multi-turn success rate by up to 63 percentage points and enhanced consistency.
Large Language Model-based agents(LLM-based agents) are increasingly deployed in customer service, yet they often forget across sessions, repeat errors, and lack mechanisms for continual self-improvement. This makes them unreliable in dynamic settings where stability and consistency are critical. To better evaluate these properties, we emphasize two indicators: task success rate as a measure of overall effectiveness, and consistency metrics such as Pass$^k$ to capture reliability across multiple trials. To address the limitations of existing approaches, we propose MemOrb, a lightweight and plug-and-play verbal reinforcement memory layer that distills multi-turn interactions into compact strategy reflections. These reflections are stored in a shared memory bank and retrieved to guide decision-making, without requiring any fine-tuning. Experiments show that MemOrb significantly improves both success rate and stability, achieving up to a 63 percentage-point gain in multi-turn success rate and delivering more consistent performance across repeated trials. Our results demonstrate that structured reflection is a powerful mechanism for enhancing long-term reliability of frozen LLM agents in customer service scenarios.