H-MAPS: Hierarchical Memory-Augmented Proactive Search Assistant for Scientific Literature
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910207781634048 |
|---|---|
| author | Nishikawa, Koji Kato, Makoto P. |
| author_facet | Nishikawa, Koji Kato, Makoto P. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10097 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | H-MAPS: Hierarchical Memory-Augmented Proactive Search Assistant for Scientific Literature Nishikawa, Koji Kato, Makoto P. Information Retrieval H.3.3; H.5.2 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. |
| title | H-MAPS: Hierarchical Memory-Augmented Proactive Search Assistant for Scientific Literature |
| topic | Information Retrieval H.3.3; H.5.2 |
| url | https://arxiv.org/abs/2605.10097 |