Scaling training data and model parameters has long driven progress in large language models (LLMs), but this paradigm is increasingly constrained by the scarcity of high-quality data and diminishing returns from rising computational costs. As a result, recent work is increasing the focus on continual learning from real-world deployment, where user interaction logs provide a rich source of authentic human feedback and procedural knowledge. However, learning from user logs is challenging due to their unstructured and noisy nature. Vanilla LLM systems often struggle to distinguish useful feedback signals from noisy user behavior, and the disparity between user log collection and model optimization (e.g., the off-policy optimization problem) further strengthens the problem. To this end, we propose UNO (User log-driveN Optimization), a unified framework for improving LLM systems (LLMsys) with user logs. UNO first distills logs into semi-structured rules and preference pairs, then employs query-and-feedback-driven clustering to manage data heterogeneity, and finally quantifies the cognitive gap between the model's prior knowledge and the log data. This assessment guides the LLMsys to adaptively filter out noisy feedback and construct different modules for primary and reflective experiences extracted from user logs, thereby improving future responses. Extensive experiments show that UNO achieves state-of-the-art effectiveness and efficiency, significantly outperforming Retrieval Augmented Generation (RAG) and memory-based baselines. We have open-sourced our code at https://github.com/bebr2/UNO .
Characterizing Delusional Spirals through Human-LLM Chat Logs
Stanford University(斯坦福大学);Carnegie Mellon University(卡内基梅隆大学);University of Chicago(芝加哥大学);Independent Researcher(独立研究者);Harvard Belfer Center(哈佛贝尔弗中心);University of Minnesota(明尼苏达大学);The University of Texas at Austin(德克萨斯大学奥斯汀分校)
Predictive Modeling: BIM Command Recommendation Based on Large-scale Usage Logs
Chair of Computing in Civil and Building Engineering, Technical University of Munich(土木与建筑工程系,慕尼黑技术大学);TUM Georg Nemetschek Institute(慕尼黑技术大学Georg Nemetschek研究所)
Cornell University(康奈尔大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Southern California(南加州大学);University of Washington(华盛顿大学)
WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
Cornell University(康奈尔大学);Samaya AI(萨马亚人工智能公司);University of Southern California(南加利福尼亚大学);University of Washington(华盛顿大学);University of Waterloo(滑铁卢大学);Nvidia(英伟达公司)