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 τ2-bench show consistent improvement across base models.
@article{arxiv.2601.08158,
title = {WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents},
author = {Yuqing Zhou and Zhuoer Wang and Jie Yuan and Hong Wang and Samson Koelle and Ziwei Zhu and Wei Niu},
journal= {arXiv preprint arXiv:2601.08158},
year = {2026}
}