H-MAPS: Hierarchical Memory-Augmented Proactive Search Assistant for Scientific Literature
2026-05-11 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors created H-MAPS, a smart tool that helps people read scientific papers more easily by guessing what extra information they might need. Instead of the reader having to stop and search manually, H-MAPS watches reading habits and asks useful questions based on what the reader might want to know. It works privately on the user's device and adapts its help depending on who is reading, as shown with two researchers from different fields getting personalized suggestions. This tool aims to reduce interruptions and confusion when looking up background information while reading.
proactive information retrievalhierarchical memoryneural retrievallatent information needsnatural language questionsuser profilingcontext ambiguityscientific readinglocal device processingreading behavior analysis
Authors
Koji Nishikawa, Makoto P. Kato
Abstract
Scientific reading is an active process that frequently requires consulting external resources, but manual keyword searching interrupts the reading flow and imposes a high cognitive load. Existing proactive information retrieval systems often suffer from context ambiguity, as they rely solely on on-screen text and ignore the reader's specific background and intent. In this demonstration, we present H-MAPS (Hierarchical Memory-Augmented Proactive Search Assistant), a proactive literature exploration assistant that resolves this ambiguity by leveraging a three-layered hierarchical memory. Triggered by implicit reading behaviors, H-MAPS articulates the user's latent information needs into explicit natural language questions and performs neural retrieval entirely on the local device to ensure privacy. We demonstrate H-MAPS using a scenario where two researchers, specializing in NLP and HCI, read the same paper. In response, the system generates profile-specific questions and retrieves distinct literature tailored to each user.