{"ID":2866977,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18713","arxiv_id":"2509.18713","title":"MemOrb: A Plug-and-Play Verbal-Reinforcement Memory Layer for E-Commerce Customer Service","abstract":"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.","short_abstract":"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 the...","url_abs":"https://arxiv.org/abs/2509.18713","url_pdf":"https://arxiv.org/pdf/2509.18713v1","authors":"[\"Yizhe Huang\",\"Yang Liu\",\"Ruiyu Zhao\",\"Xiaolong Zhong\",\"Xingming Yue\",\"Ling Jiang\"]","published":"2025-09-23T06:57:07Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}