Vela: User Behavior as Supervision Sparks LLM Intelligence

Yang Xiao, Yusong Sun, Haoyi Wu, Wenyang Hui, Weiqiang Hang, Luqing Wang, Zejian Wang, Zirui Tu, Jingsheng Mao, Shaobo Hu, Yang Luo, Jiale Guo, Jin Zhang, Yudan Liu, Zhaokai Luo, Ren Huan, Yao Hu, Chengyue Jiang, Wenjie Li, Chuan Mu

2026 · AllSpark at Xiaohongshu

Privacy statement. Behavior records were anonymized before task construction. Their use was authorized by the platform and underwent privacy and ethics review.

Abstract

Large language models are increasingly deployed in real-world applications, from personal assistants that take actions based on users' long-term behavior histories to recommendation and advertising systems that predict what users will do. These applications demand the user dimension of LLM intelligence: the ability to infer a person's preferences, intent, and likely future actions from weeks to years of user behavior data. Yet current models remain limited in this user dimension of intelligence: they are trained on static text or synthetic data, neither of which captures how user behavior evolves over time. Real-world user behavior data, by contrast, is already available at scale on content platforms and in personal-assistant agents. These records capture sequences of user actions, making the user's actual behavior a natural supervisory signal with the potential to improve LLM intelligence. To this end, we propose user behavior as supervision, a paradigm in which the training signal for LLMs comes from the user's real behavior in content platforms. We further introduce Vela, a framework that operationalizes this paradigm by converting real user behavior data into trainable tasks and trajectories. From the anonymized behavior records of 100,000 users, Vela generates 100,000 tasks across 91 real-world task templates. Difficulty-based filtering and trajectory acceptance criteria jointly retain approximately 75,000 tasks with selected training trajectories. Fine-tuning Qwen3.6-35B-A3B on these training trajectories improves performance over the base model by up to 11.5 points on user-related tasks and by an average of 4 points on general benchmarks. Scaling experiments further show that training on more user behavior data improves user-related performance. Reinforcement learning after fine-tuning outperforms reinforcement learning from the base model by up to 7.7 points on user-related tasks. These gains suggest that using real-world user behavior as supervision can improve not only user-centered capabilities but also the broader intelligence of LLMs.