Sci-Surf: Navigating Scientific Literature Discovery through Human Feedback and Intelligent Summarizatio
For researchers overwhelmed by the volume of publications, Sci-Surf offers a more intent-centric and digestible alternative to existing discovery platforms, but the gains are modest and the system is domain-specific.
Sci-Surf is an academic discovery system that combines feedback-driven personalized recommendations with multi-modal blog-style paper summaries. In a month-long online evaluation, it achieved a 10.4% average improvement in predictive alignment with real-world user preferences.
The rapid growth of scientific publications makes it increasingly difficult for researchers to identify relevant new studies and effectively comprehend them. Existing academic discovery platforms typically rely on static topic subscriptions or embedding-based similarity and provide only abstracts or short summaries, offering limited support for nuanced intent modeling and in-depth paper summarization. We present Sci-Surf, an intent-centric knowledge discovery system that integrates feedback-driven personalized recommendation with multi-modal blog-style paper digestion. Our approach refines user intent representations through LLM-based user profiling, while generating structured summaries that synthesize textual and visual information from full papers. The demo presents an end-to-end academic discovery pipeline and demonstrates measurable improvements in both recommendation quality and digestion quality through real-user evaluations. Specifically, the integration of verbalized profiles led to a 10.4% average improvement in predictive alignment with real-world user preferences throughout a month-long online evaluation.