While existing work focuses primarily on task success, we argue that effective real-world agents require optimizing three dimensions: productivity (task completion), proactivity (asking essential questions), and personalization (adapting to diverse user preferences). We introduce UserVille, an interactive environment with LLM-based user simulators enabling diverse, configurable user preferences. Leveraging UserVille, we introduce PPP, a multi-objective reinforcement learning approach that jointly optimizes all three dimensions: Productivity, Proactivity, and Personalization. Experiments on software engineering and deep research tasks show that agents trained with PPP achieve substantial improvements over strong baselines such as GPT-5 (+21.6 on average), demonstrating the ability to ask strategic clarifying questions, adapt to unseen user preferences, and improve task success through better interaction. This work demonstrates that explicitly optimizing for user-centered interaction is critical for building practical and effective AI agents.
@article{arxiv.2511.02208,
title = {Training Proactive and Personalized LLM Agents},
author = {Weiwei Sun and Xuhui Zhou and Weihua Du and Xingyao Wang and Sean Welleck and Graham Neubig and Maarten Sap and Yiming Yang},
journal= {arXiv preprint arXiv:2511.02208},
year = {2025}
}