用智能代理闭环优化推荐排序，自动调节影响分配提升业务指标。
Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange
- 将排序优化看作持续的影响交换，通过双通道机制解耦离线与在线偏差。
- 在两国市场实现GMV显著提升，最高达+12.5%订单增长，冷启动7天内广告收入增3.58%。
- 适合需要自动化推荐调优的工业级系统，尤其适用于复杂影响权衡场景。
推荐排序本质上是影响力分配问题：排序公式在竞争因素间分配影响力，业务结果取决于找到最优的“交换率”。然而，离线代理指标会系统性误判影响力重分配对线上效果的影响，且不同指标间存在不对称偏差，单一校准因子无法纠正。我们提出Sortify，首个在大规模生产推荐系统中部署的全自主大模型驱动排序优化代理。该代理将排序优化重构为连续的影响交换过程，实现从诊断到参数部署的完整闭环，无需人工干预。其解决结构性问题的三重机制包括：(1) 基于萨维奇主观期望效用（SEU）的双通道框架，分离离线-在线迁移修正（信念通道）与约束惩罚调整（偏好通道）；(2) 由大模型担任元控制器，操作框架级参数而非底层搜索变量；(3) 持久化内存数据库，包含7个关系表支持跨轮次学习。核心指标“Influence Share”提供可分解的度量，所有因素贡献之和恰好为100%。Sortify已在两个市场部署：在国家A，7轮迭代后GMV从-3.6%提升至+9.2%，峰值订单增长达+12.5%；在国家B，冷启动部署在7天A/B测试中实现GMV/UU提升+4.15%、广告收入提升+3.58%，随后全面上线生产环境。
原文摘要 · Abstract (English)
Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends on finding the optimal "exchange rates" among them. However, offline proxy metrics systematically misjudge how influence reallocation translates to online impact, with asymmetric bias across metrics that a single calibration factor cannot correct. We present Sortify, the first fully autonomous LLM-driven ranking optimization agent deployed in a large-scale production recommendation system. The agent reframes ranking optimization as continuous influence exchange, closing the full loop from diagnosis to parameter deployment without human intervention. It addresses structural problems through three mechanisms: (1) a dual-channel framework grounded in Savage's Subjective Expected Utility (SEU) that decouples offline-online transfer correction (Belief channel) from constraint penalty adjustment (Preference channel); (2) an LLM meta-controller operating on framework-level parameters rather than low-level search variables; (3) a persistent Memory DB with 7 relational tables for cross-round learning. Its core metric, Influence Share, provides a decomposable measure where all factor contributions sum to exactly 100%. Sortify has been deployed across two markets. In Country A, the agent pushed GMV from -3.6% to +9.2% within 7 rounds with peak orders reaching +12.5%. In Country B, a cold-start deployment achieved +4.15% GMV/UU and +3.58% Ads Revenue in a 7-day A/B test, leading to full production rollout.
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。