arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.09579cs.AIcs.SE
收藏

无需被要求的帮助:一个用于轮班支持的主动代理系统,具备持续自我改进

Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement

ByteDance(字节跳动)

Fengrui Liu, Xiao He, Tieying Zhang

AI总结:

本文提出Vigil系统,通过主动提供帮助减少人工支持负担,持续学习提升能力,已在Volcano Engine部署超过十个月,验证其有效性。

摘要:

在大规模云服务平台中,每天生成数千张客户工单,通常通过轮班对话处理。大量轮班交互对人类支持分析师造成巨大负担。近期研究探索了利用大语言模型的反应式代理,直接与客户互动解决问题。然而,当问题未解决并升级至人类支持时,这些代理通常退出。因此,它们无法帮助后续查询、跟踪解决进度或从未能解决的案例中学习。本文介绍Vigil,一种新型主动代理系统,贯穿整个轮班生命周期。不同于反应式代理,Vigil专注于在人类支持已介入的阶段提供帮助。它整合到客户与分析师之间的对话中,主动提供帮助而无需显式用户调用。此外,Vigil包含持续自我改进机制,从人类解决的案例中提取知识,自主更新其能力。Vigil已在Volcano Engine部署超过十个月,基于此部署的全面评估证明其有效性和实用性。此工作的开源版本在https://github.com/volcengine/veaiops公开。

英文摘要:

In large-scale cloud service platforms, thousands of customer tickets are generated daily and are typically handled through on-call dialogues. This high volume of on-call interactions imposes a substantial workload on human support analysts. Recent studies have explored reactive agents that leverage large language models as a first line of support to interact with customers directly and resolve issues. However, when issues remain unresolved and are escalated to human support, these agents are typically disengaged. As a result, they cannot assist with follow-up inquiries, track resolution progress, or learn from the cases they fail to address. In this paper, we introduce Vigil, a novel proactive agent system designed to operate throughout the entire on-call life-cycle. Unlike reactive agents, Vigil focuses on providing assistance during the phase in which human support is already involved. It integrates into the dialogue between the customer and the analyst, proactively offering assistance without explicit user invocation. Moreover, Vigil incorporates a continuous self-improvement mechanism that extracts knowledge from human-resolved cases to autonomously update its capabilities. Vigil has been deployed on Volcano Engine, ByteDance's cloud platform, for over ten months, and comprehensive evaluations based on this deployment demonstrate its effectiveness and practicality. The open source version of this work is publicly available at https://github.com/volcengine/veaiops.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑