COPE (Continual Optimization with Personalized embedding and self-Evaluation) is a new framework that continually personalizes large language models using learnable user embeddings and self‑evaluation to generate proxy rewards. It integrates preference capture, self‑evaluation calibration, and personalized response optimization into a single update step, allowing continuous model updates even when explicit user feedback is sparse. Experiments demonstrate that COPE outperforms both training‑free and training‑based baselines, remains complementary to Retrieval‑Augmented Prompting, and shows reliable self‑evaluation, meaningful preference patterns, stable general capabilities, and robustness to shifting preferences and alternative evaluators.
By Ruike Cao, Fugen Yao, Liang Dong, Jian Xu, Guanjun Jiang, Li Xiao
arXiv:2606. 21097v2 Announce Type: replace-cross Abstract: Deploying highly capable personalized conversational agents in resource-constrained or privacy-sensitive environments remains a significant challenge.
By Junfeng Liu, Christopher T. Symons, Ranga Raju Vatsavai
arXiv:2607. 26473v1 Announce Type: new Abstract: Personalizing large language models (LLMs) to individual users is essential for improving user experience, yet existing approaches typically rely on explicit preference supervision such as pairwise comparisons or demographic attributes, limiting their applicability in natural interaction settings.
By Haifeng Wu
arXiv:2603.04191v2 Announce Type: replace
Abstract: Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interactio...
By Qianyun Guo, Yibo Li, Yue Liu, Bryan Hooi
Personalizing large language models (LLMs) to individual users is essential for improving user experience, yet existing approaches typically rely on explicit preference supervision such as pairwise comparisons or demographic attributes, limiting their applicability in natural interaction settings. We propose IRIS, a framework that learns dynamic user personas directly from implicit interaction streams by extracting behavioral signals from everyday conversations and iteratively refining persona representations through a prediction-driven closed loop without requiring explicit feedback.
arXiv:2607. 00010v1 Announce Type: cross Abstract: Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to actively elicit preferences, clarify intentions, and adapt recommendations in real time.
By Nipun B Nair, Tongtong Wu, Weiqing Wang
arXiv:2606. 06614v1 Announce Type: cross Abstract: Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data.
By Lechen Zhang, Jiarui Liu, Tal August
arXiv:2609.00251v1 Announce Type: new
Abstract: As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective lo...
By EunJeong Hwang, Kushan Mitra, Dan Zhang, Hannah Kim, Estevam Hruschka
arXiv:2608. 05246v1 Announce Type: new Abstract: Existing personalized LLM benchmarks primarily rely on textual personas or isolated behavioral signals, providing limited evaluation of cross-domain behavioral personalization, where responses must be grounded in heterogeneous daily-life activities.
By Jiahao Zhang, Yongzhi Tong, Zelin Fu, Pengde Zhao, Yanmei Jiang, Jiang Feng, Min Yang
arXiv:2609.00014v1 Announce Type: cross
Abstract: Persona-driven techniques increasingly adapt large language models (LLMs) to diverse contexts. However, existing methods predominantly rely on rigid,...
By Yuxuan Li, Victor Zhong, Ehsan Kamalloo
arXiv:2609.14648v1 Announce Type: new
Abstract: Aligning multi-turn dialogue agents is usually framed as matching turn-level human preferences, yet direct optimization of long-term outcomes is often...
By Ziyi Zhu, Daniel R. Cahn, Thomas D. Hull, Caitlin A. Stamatis, Olivier Tieleman, Guilherme B. Freire, Jinghong Chen
The paper surveys how AI copilots—AI-powered assistants for knowledge workers and developers—can personalize their behavior by optimizing user preferences. It reviews how preference signals are collected, modeled at different interaction stages, and refined through feedback loops, and introduces a taxonomy of optimization techniques for pre-, mid-, and post-interaction phases. The study evaluates each technique’s strengths, limitations, and design implications, aiming to unify efforts across AI personalization, human‑AI interaction, and language model adaptation.
By Saleh Afzoon, Ali Shahsavandi, Phuong Thao Huynh, Melika Zare, Zahra Jahanandish, Amin Beheshti, Usman Naseem