PersonaX：面向长行为序列的推荐智能体用户建模框架
PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence
AI总结：
针对推荐智能体中长行为序列建模的挑战，提出与智能体无关的LLM-UM框架PersonaX，通过聚类分段、多样化子序列选择、离线多画像生成及推理解耦，仅用30-50%数据提升AgentCF和Agent4Rec性能3-50%。
摘要：
嵌入在个性化推荐智能体提示模板中的用户画像在塑造其决策过程中起着至关重要的作用。高质量的用户画像对于使智能体行为与真实用户兴趣保持一致至关重要。通常，这些画像通过利用大语言模型进行用户建模（LLM-UM）来构建。然而，这一过程面临若干挑战：（1）由于上下文长度限制和性能下降，大语言模型难以处理长用户行为。（2）现有方法通常仅从完整历史行为序列中提取部分片段，不可避免地丢弃了被省略内容中蕴含的多样化用户兴趣，导致建模不完整和画像次优。（3）用户画像通常与推理上下文紧密耦合，需要在线处理，这引入了显著的延迟开销。在本文中，我们提出PersonaX，一个与智能体无关的LLM-UM框架，以解决这些挑战。它增强了下游推荐智能体，以实现更好的推荐性能和推理效率。PersonaX（a）将完整历史行为分割成聚类组，（b）在原型性和多样性之间取得平衡，选择多个子行为序列（SBS）以形成高质量的核心集，（c）执行离线多画像建模以捕获多样化用户兴趣并生成细粒度的、缓存的文本画像，以及（d）将用户建模与在线推理解耦，实现画像检索而非实时生成。大量实验证明了其有效性：仅使用30%至50%的行为数据（序列长度480），PersonaX使AgentCF提升3%至11%，使Agent4Rec提升10%至50%。作为可扩展且与模型无关的LLM-UM解决方案，PersonaX在可扩展用户建模领域树立了新的基准。
英文摘要：
User profile embedded in the prompt template of personalized recommendation agents play a crucial role in shaping their decision-making process. High-quality user profiles are essential for aligning agent behavior with real user interests. Typically, these profiles are constructed by leveraging LLMs for user profile modeling (LLM-UM). However, this process faces several challenges: (1) LLMs struggle with long user behaviors due to context length limitations and performance degradation. (2) Existing methods often extract only partial segments from full historical behavior sequence, inevitably discarding diverse user interests embedded in the omitted content, leading to incomplete modeling and suboptimal profiling. (3) User profiling is often tightly coupled with the inference context, requiring online processing, which introduces significant latency overhead. In this paper, we propose PersonaX, an agent-agnostic LLM-UM framework to address these challenges. It augments downstream recommendation agents to achieve better recommendation performance and inference efficiency. PersonaX (a) segments complete historical behaviors into clustered groups, (b) selects multiple sub behavior sequences (SBS) with a balance of prototypicality and diversity to form a high quality core set, (c) performs offline multi-persona profiling to capture diverse user interests and generate fine grained, cached textual personas, and (d) decouples user profiling from online inference, enabling profile retrieval instead of real time generation. Extensive experiments demonstrate its effectiveness: using only 30 to 50% of behavioral data (sequence length 480), PersonaX enhances AgentCF by 3 to 11% and Agent4Rec by 10 to 50%. As a scalable and model-agnostic LLM-UM solution, PersonaX sets a new benchmark in scalable user modeling.
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。
