Evaluating Large Language Models as Domain-Specific Retrieval Agents: A Study on Cybersecurity Challenge Benchmarks.

@inproceedings{abed-2026-evaluating, author = {Omed Abed and Md. Samiul Haque and Patrick-Benjamin B\"{o}k and Matteo Gro{\ss}e-Kampmann}, editor = {Ricardo Campos and Adam Jatowt and Yanyan Lan and Mohammad Aliannejadi and Christine Bauer and Sean MacAvaney and Avishek Anand and Zhaochun Ren and Suzan Verberne and Nan Bai and Masoud Mansoury}, title = {{Evaluating Large Language Models as Domain-Specific Retrieval Agents: A Study on Cybersecurity Challenge Benchmarks}}, booktitle = {{Advances in Information Retrieval - 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, March 29 - April 2, 2026, Proceedings, Part II}}, series = {Lecture Notes in Computer Science}, volume = {16484}, pages = {328--337}, publisher = {Springer}, year = {2026}, url = {https://doi.org/10.1007/978-3-032-21300-6_23}, doi = {https://doi.org/10.1007/978-3-032-21300-6_23} }