Details
| Original language | English |
|---|---|
| Title of host publication | Scientific Knowledge: Representation, Discovery, and Assessment 2025 |
| Subtitle of host publication | Proceedings of the 5th International Workshop on Scientific Knowledge: Representation, Discovery, and Assessment co-located with 24th International International Semantic Web Conference (ISWC 2025) |
| Pages | 149-157 |
| Number of pages | 9 |
| Publication status | Published - 13 Oct 2025 |
| Event | 5th International Workshop on Scientific Knowledge, Sci-K 2025: Representation, Discovery, and Assessment - Nara, Japan Duration: 2 Nov 2025 → 2 Nov 2025 |
Publication series
| Name | CEUR Workshop Proceedings |
|---|---|
| Publisher | CEUR Workshop |
| Volume | 4065 |
| ISSN (Print) | 1613-0073 |
Abstract
In the fast-evolving era of agentic AI, Large Language Models (LLMs) from major providers and open-source alternatives offer unprecedented capabilities for “deep search”, enabling complex, iterative information retrieval and synthesis crucial for academic endeavors. However, their application in scientific research and paper writing necessitates strict requirements and a critical awareness of inherent limitations, including the risks of unreviewed content, temporal biases, and access barriers such as paywalls. This vision paper discusses a list of requirements that a scientific deep research system should have to become a viable candidate (i.e., to become a valuable system for researchers). As well as a list of limitations that are observed from current systems (industry-grade and community-developed). We also outline a path forward for harnessing agentic AI in scientific discovery and scholarly communication.
Keywords
- Agentic AI, Deep (Re)Search, Information Asymmetry, Unreviewed Content Risks
ASJC Scopus subject areas
- Computer Science(all)
- General Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Scientific Knowledge: Representation, Discovery, and Assessment 2025: Proceedings of the 5th International Workshop on Scientific Knowledge: Representation, Discovery, and Assessment co-located with 24th International International Semantic Web Conference (ISWC 2025). 2025. p. 149-157 (CEUR Workshop Proceedings; Vol. 4065).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Deep Research in the Era of Agentic AI
T2 - 5th International Workshop on Scientific Knowledge, Sci-K 2025
AU - Jaradeh, Mohamad Yaser
AU - Auer, Sören
N1 - Publisher Copyright: © 2025 Copyright for this paper by its authors.
PY - 2025/10/13
Y1 - 2025/10/13
N2 - In the fast-evolving era of agentic AI, Large Language Models (LLMs) from major providers and open-source alternatives offer unprecedented capabilities for “deep search”, enabling complex, iterative information retrieval and synthesis crucial for academic endeavors. However, their application in scientific research and paper writing necessitates strict requirements and a critical awareness of inherent limitations, including the risks of unreviewed content, temporal biases, and access barriers such as paywalls. This vision paper discusses a list of requirements that a scientific deep research system should have to become a viable candidate (i.e., to become a valuable system for researchers). As well as a list of limitations that are observed from current systems (industry-grade and community-developed). We also outline a path forward for harnessing agentic AI in scientific discovery and scholarly communication.
AB - In the fast-evolving era of agentic AI, Large Language Models (LLMs) from major providers and open-source alternatives offer unprecedented capabilities for “deep search”, enabling complex, iterative information retrieval and synthesis crucial for academic endeavors. However, their application in scientific research and paper writing necessitates strict requirements and a critical awareness of inherent limitations, including the risks of unreviewed content, temporal biases, and access barriers such as paywalls. This vision paper discusses a list of requirements that a scientific deep research system should have to become a viable candidate (i.e., to become a valuable system for researchers). As well as a list of limitations that are observed from current systems (industry-grade and community-developed). We also outline a path forward for harnessing agentic AI in scientific discovery and scholarly communication.
KW - Agentic AI
KW - Deep (Re)Search
KW - Information Asymmetry
KW - Unreviewed Content Risks
UR - http://www.scopus.com/inward/record.url?scp=105019645221&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:105019645221
T3 - CEUR Workshop Proceedings
SP - 149
EP - 157
BT - Scientific Knowledge: Representation, Discovery, and Assessment 2025
Y2 - 2 November 2025 through 2 November 2025
ER -