让电商图像助手自动进化技能，精准识别用户意图。
SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants
- 通过三阶段自动化流程构建与优化技能，闭环管理技能演化。
- 线上实验显示用户留存和内容消费显著提升，结构合规性改善明显。
- 适合需要动态适配多类用户意图的生产级视觉AI系统使用。
基于图像的AI助手已在电商平台大规模部署，单张上传图片可能触发多种用户意图：商品搜索、风格推荐、视觉百科或工具调用，每种意图需不同响应格式、工具调用和领域知识。缺乏针对意图的行为约束时，大模型系统会混淆这些异构模式，难以满足领域质量标准；而意图空间的广度与动态性使得人工工程不可行。为此，我们提出SkillChain，通过三个阶段实现技能演化的生产闭环：技能创建器从任务规范和轨迹中启动技能，路由优化器对齐路由策略，体部精炼器通过双路径大模型-裁判评估实现技能体的迭代优化。在生产规模的电商图像助手上部署后，SkillChain显著提升综合响应质量，尤其在结构合规性和内容质量上效果突出；为期一周的线上A/B实验进一步验证了用户参与度、内容消费量及长期留存率的显著提升。
原文摘要 · Abstract (English)
Image-based AI assistants are now deployed at production scale on e-commerce platforms, where a single uploaded image can trigger fundamentally different user intents: product search, style recommendation, visual encyclopedia, or utility tool calls, each demanding its own response format, tool invocation, and domain knowledge. Without per-intent behavioral constraints, LLM-based systems conflate these heterogeneous modes and fall short of domain quality standards, while the breadth and dynamism of the intent space render manual engineering infeasible. To address this, we present SkillChain, which closes the production feedback loop on Skill evolution, automating the lifecycle of Skills through three stages: Skill Creator for bootstrapping from task specs and trajectories, Route Optimizer for routing alignment, and Body Refiner for iterative Skill Body refinement via dual-path LLM-Judge evaluation. Deployed on a production-scale e-commerce image assistant, SkillChain substantially improves aggregate response quality, with the strongest gains on structural compliance and content quality; a one-week online A/B experiment further confirms significant gains in user engagement, content consumption, and long-term retention.
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。