EUVIMEDEUVIMED entdecken
Crossref

LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation

Gregory Hok Tjoan Go, Khang Ly, Anders Søgaard, Seyed Amin Tabatabaei, Maarten de Rijke, Xinyi Chen

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 40456-40464

DOI: 10.1609/aaai.v40i47.41489 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Gregory Hok Tjoan Go und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of scientific publications has made it increasingly difficult to keep literature reviews comprehensive and up-to-date. Though prior work has focused on automating retrieval and screening, the writing phase of systematic reviews remains largely under-explored, especially with regard to readability and factual accuracy. To address this, we present LiRA (Literature Review Agents), a multi-agent collaborative workflow which emulates the human literature review process. LiRA utilizes specialized agents for content outlining, subsection writing, editing, and reviewing, producing cohesive and comprehensive review articles. Evaluated on SciReviewGen and a proprietary ScienceDirect dataset, LiRA outperforms current baselines such as AutoSurvey and MASS-Survey in writing and citation quality, while maintaining competitive similarity to human-written reviews. We further evaluate LiRA in real-world scenarios using document retrieval and assess its robustness to reviewer model variation. Our findings highlight the potential of agentic LLM workflows, even without domain-specific tuning, to improve the reliability and usability of automated scientific writing.

Zitieren

APA

Go, G. H. T., Ly, K., Søgaard, A., Tabatabaei, S. A., Rijke, M. D., & Chen, X. (2026). LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 40456-40464. https://doi.org/10.1609/aaai.v40i47.41489

Vancouver

Go GHT, Ly K, Søgaard A, Tabatabaei SA, Rijke MD, Chen X. LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):40456-40464. doi:10.1609/aaai.v40i47.41489

BibTeX
@article{Go2026,
  author = {Go, Gregory Hok Tjoan and Ly, Khang and Søgaard, Anders and Tabatabaei, Seyed Amin and Rijke, Maarten de and Chen, Xinyi},
  title = {LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {47},
  pages = {40456--40464},
  doi = {10.1609/aaai.v40i47.41489}
}
Kostenlos starten →