让聊天机器人从历史对话中自动提炼流程经验，自我改进错误。
WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents
- 将历史交互转化为带前提条件的动作流程，形成可复用经验
- 部署时通过匹配流程并推理可行性，减少执行偏差
- 适合需要持续优化的客服类大模型应用
基于大语言模型的智能体广泛应用于用户服务场景，但在新任务中仍易出错、重复失败且运行结果波动大。通过环境定制训练或人工修复成本高且难以扩展。为实现服务场景中自演化智能体，我们提出 WISE-Flow 框架，通过引入前提增强的动作块，将历史服务交互转化为可复用的流程化经验。部署时，该框架将智能体执行轨迹与检索到的流程对齐，并进行前提感知的可行性推理，以生成符合当前状态的下一步动作。在 ToolSandbox 与 $τ^2$-bench 数据集上的实验表明，该方法在不同基础模型上均实现了稳定提升。
原文摘要 · Abstract (English)
Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks, tend to repeat the same failure patterns, and show substantial run-to-run variability. Fixing failures via environment-specific training or manual patching is costly and hard to scale. To enable self-evolving agents in user-facing service environments, we propose WISE-Flow, a workflow-centric framework that converts historical service interactions into reusable procedural experience by inducing workflows with prerequisite-augmented action blocks. At deployment, WISE-Flow aligns the agent's execution trajectory to retrieved workflows and performs prerequisite-aware feasibility reasoning to achieve state-grounded next actions. Experiments on ToolSandbox and $τ^2$-bench show consistent improvement across base models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。