UserGPT Technical Report
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914547686703104 |
|---|---|
| author | Xuan, Yunyi Yi, Hao Mao, Fengling Cai, Daye Liang, Leikun He, Xingsheng Xie, Jiangnan Wang, Guoshuai Han, Yushan Guo, Wenwen Xu, Xiaoxiao Qu, Lin |
| author_facet | Xuan, Yunyi Yi, Hao Mao, Fengling Cai, Daye Liang, Leikun He, Xingsheng Xie, Jiangnan Wang, Guoshuai Han, Yushan Guo, Wenwen Xu, Xiaoxiao Qu, Lin |
| contents | Personalized user understanding from large-scale digital traces remains a fundamental challenge. Traditional user profiling methods rely on discriminative models and manual feature engineering to predict discrete attributes, often producing fragmented and logically inconsistent profiles that generalize poorly to long-tail behaviors. In this work, we study a generative paradigm in which large language models (LLMs) summarize long and noisy behavioral histories into coherent narratives that capture nuanced user evolution. Our experiments show that even strong LLMs remain limited in complex and implicit personalization reasoning.
We propose UserGPT, a framework for improving LLM-based persona understanding through both attribute generation and summary generation. To address the scarcity of real-world behavioral data, we develop a User Behavior Simulation Engine that produces realistic and complex user trajectories. We further introduce a Data-Centric Semantization module that transforms heterogeneous behavioral logs into structured and semantically coherent inputs, reducing noise and sparsity. On top of this pipeline, we design a curriculum-driven post-training strategy that combines multi-stage Supervised Fine-Tuning (SFT) with Dual-Filter Group Relative Policy Optimization (DF-GRPO) to strengthen reasoning over long behavioral histories.
We also construct HPR-Bench, a benchmark for holistic persona reasoning derived from simulated data. On HPR-Bench, UserGPT achieves an Avg@10 score of 0.7325 on tag prediction and an $Acc_{Ex}$ score of 0.7528 on summary generation, while compressing behavioral records by up to 97.9% with critical information preserved. These results demonstrate the effectiveness of UserGPT for holistic persona reasoning and personalized user-agent interaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08766 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UserGPT Technical Report Xuan, Yunyi Yi, Hao Mao, Fengling Cai, Daye Liang, Leikun He, Xingsheng Xie, Jiangnan Wang, Guoshuai Han, Yushan Guo, Wenwen Xu, Xiaoxiao Qu, Lin Information Retrieval Computation and Language Personalized user understanding from large-scale digital traces remains a fundamental challenge. Traditional user profiling methods rely on discriminative models and manual feature engineering to predict discrete attributes, often producing fragmented and logically inconsistent profiles that generalize poorly to long-tail behaviors. In this work, we study a generative paradigm in which large language models (LLMs) summarize long and noisy behavioral histories into coherent narratives that capture nuanced user evolution. Our experiments show that even strong LLMs remain limited in complex and implicit personalization reasoning. We propose UserGPT, a framework for improving LLM-based persona understanding through both attribute generation and summary generation. To address the scarcity of real-world behavioral data, we develop a User Behavior Simulation Engine that produces realistic and complex user trajectories. We further introduce a Data-Centric Semantization module that transforms heterogeneous behavioral logs into structured and semantically coherent inputs, reducing noise and sparsity. On top of this pipeline, we design a curriculum-driven post-training strategy that combines multi-stage Supervised Fine-Tuning (SFT) with Dual-Filter Group Relative Policy Optimization (DF-GRPO) to strengthen reasoning over long behavioral histories. We also construct HPR-Bench, a benchmark for holistic persona reasoning derived from simulated data. On HPR-Bench, UserGPT achieves an Avg@10 score of 0.7325 on tag prediction and an $Acc_{Ex}$ score of 0.7528 on summary generation, while compressing behavioral records by up to 97.9% with critical information preserved. These results demonstrate the effectiveness of UserGPT for holistic persona reasoning and personalized user-agent interaction. |
| title | UserGPT Technical Report |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2605.08766 |