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 2604.14972cs.IR
收藏

SAGER:面向推荐代理的自进化用户策略技能

SAGER: Self-Evolving User Policy Skills for Recommendation Agent

Great Bay University(大湾区大学);Hong Kong Baptist University(香港浸会大学);Sun Yat-Sen University(中山大学);Platform and Content Group, Tencent(腾讯平台与内容事业群)

Zhen Tao, Riwei Lai, Chenyun Yu, Weixin Chen, Li Chen, Beibei Kong, Lei Cheng, Chengxiang Zhuo, Zang Li, Qingqiang Sun

AI总结:

SAGER通过为每个用户分配专用策略技能,实现个性化推荐代理的自进化推理,实验表明其在四个公开基准上达到最优性能,证明个性化推理过程是推荐改进的新来源。

摘要:

基于大型语言模型(LLM)的推荐代理通过进化个性化语义记忆来个性化其知识,但其推理仍依赖于一个通用、静态的系统提示。这种不对称性是瓶颈:当推荐失败时,代理更新用户偏好记忆但不检查导致失败的决策逻辑,推理过程结构不变。为此,我们提出SAGER(自进化推荐代理框架),每个用户配备专用策略技能,通过交互持续进化。SAGER引入双表示技能架构,分离丰富进化基质与最小推理时间注入,增量对比链式思考引擎通过对比接受与未选择项诊断推理缺陷,技能增强列表推理创建细粒度决策边界。实验表明SAGER在四个公开基准上达到最优性能,证明个性化推理过程是推荐改进的新来源。

英文摘要:

Large language model (LLM) based recommendation agents personalize what they know through evolving per-user semantic memory, yet how they reason remains a universal, static system prompt shared identically across all users. This asymmetry is a fundamental bottleneck: when a recommendation fails, the agent updates its memory of user preferences but never interrogates the decision logic that produced the failure, leaving its reasoning process structurally unchanged regardless of how many mistakes it accumulates. To address this bottleneck, we propose SAGER (Self-Evolving Agent for Personalized Recommendation), the first recommendation agent framework in which each user is equipped with a dedicated policy skill, a structured natural-language document encoding personalized decision principles that evolves continuously through interaction. SAGER introduces a two-representation skill architecture that decouples a rich evolution substrate from a minimal inference-time injection, an incremental contrastive chain-of-thought engine that diagnoses reasoning flaws by contrasting accepted against unchosen items while preserving accumulated priors, and skill-augmented listwise reasoning that creates fine-grained decision boundaries where the evolved skill provides genuine discriminative value. Experiments on four public benchmarks demonstrate that SAGER achieves state-of-the-art performance, with gains orthogonal to memory accumulation, confirming that personalizing the reasoning process itself is a qualitatively distinct source of recommendation improvement.

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。

↑