PersonaX: A Recommendation Agent-Oriented User Modeling Framework for Long Behavior Sequence

ACL ARR 2025 February Submission59 Authors

Abstract:

Recommendation agents leverage large language models for user modeling (LLM-UM) to construct textual personas, guiding alignment with real users. However, existing LLM-UM methods struggle with long user-generated content (UGC) due to context limitations and performance degradation.
To address this, sampling strategies prioritize relevance or recency are often applied, yet they inevitably neglect the diverse user interests embedded within the discarded behaviors, resulting in incomplete modeling and degraded profiling quality. Furthermore, relevance-based sampling requires real-time retrieval, forcing the user modeling process to operate online, which introduces significant latency overhead.
In this paper, we propose PersonaX, an agent-agnostic LLM-UM framework that tackles these challenges through sub-behavior sequence (SBS) selection and offline multi-persona construction. PersonaX extracts compact SBS segments offline to capture diverse user interests, generating fine-grained textual personas that are cached for efficient online retrieval. This approach ensures that the user persona used for prompting remains highly relevant to the current context, while eliminating the need for online user modeling. For SBS selection, we ensure both efficiency (length $<5$) and high representational quality by balancing prototypicality and diversity within the sampled data.
Extensive experiments validate the effectiveness and versatility of PersonaX in high-quality user profiling. Utilizing only 30–50\% of the behavioral data with a sequence length of 480, integrating PersonaX with AgentCF yields an absolute performance improvement of 3–11\%, while integration with Agent4Rec results in a gain of 10–50\%. PersonaX as an agent-agnostic framework, sets a new benchmark for scalable user modeling, paving the way for more accurate and efficient LLM-driven recommendation agents.

Paper Type: Long

Research Area: Computational Social Science and Cultural Analytics

Research Area Keywords: human behavior analysis, data augmentation, NLP in resource-constrained settings, user-centered design, long-form summarization

Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency, Data analysis

Languages Studied: English

Submission Number: 59