Sahel Sharifymoghaddam

Hi! I am a fourth-year PhD student in the David R. Cheriton School of Computer Science at the University of Waterloo, where I am fortunate to be supervised by Professor Jimmy Lin. My broad research interests lie at the intersection of Information Retrieval (IR) and Natural Language Processing (NLP), with a focus on agentic search, ranking, retrieval-augmented generation (RAG), grounding, and their multimodal extensions. During my Ph.D., I worked part-time as an AI consultant at Yupp (2025) and interned with the NeMo Retriever team at NVIDIA (2026), where I built ACARe, an agent-context-aware reranker for iterative search.

Before starting my Ph.D., I worked as a Software Engineer at Google, first on Google Chrome, and later on the Google Cloud-Applied AI team. At Applied AI, we built applications using Generative AI and cloud infrastructure. This followed my M.A.Sc. in Computer Engineering from the University of Toronto in 2015, advised by Professor Cristiana Amza. I earned my Bachelor's degree from Sharif University of Technology, Iran, in 2013. My complete CV is available here (last updated Nov. 2025).

Email  /  Google Scholar  /  LinkedIn  /  GitHub  /  (Formerly Twitter)

portrait of Sahel Sharifymoghaddam

👭 Fun fact: I have a twin sister, Sayeh, who also works in machine learning and publishes under the name “S. Sharify.” It’s easy to confuse “S. Sharifymoghaddam” with “S. Sharify”--even Google Scholar does at times! While we share initials (and interests), the credit for her work is entirely hers.

Selected Publications

ACARe: Agent-Context-Aware Reranker for Iterative Search


Sharifymoghaddam, S., Babakhin, Y., Esfandiarpoor, R., Holworthy, O., Lin, J., & Liu, B.
Preprint (arXiv 2026)
bib / paper

Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search


Lin, J., Sharifymoghaddam, S., Gu, L., & Jedidi, N.
Preprint (arXiv 2026)
bib / paper

CMASS: A ClimbMix Agentic Search Suite for Evaluating Search Agents Across Heterogeneous Tasks


Sharifymoghaddam, S.*, Gu, L.*, Ge, Y., & Lin, J.
Preprint (arXiv 2026)
bib / paper / website / code / data

MCP Servers for Pyserini and RankLLM: Enabling Agentic Retrieval-Augmented Generation


Ge, Y., Guo, Z., Sharifymoghaddam, S., & Lin, J.
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2026) , pp. 5156--5160
bib / paper

Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents


Sharifymoghaddam, S., & Lin, J.
Findings of the Association for Computational Linguistics (ACL 2026) , pp. 25874--25886
bib / paper / code

Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM


Sharifymoghaddam, S.*, Ge, Y.*, Vasudeva, R., & Lin, J.
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2026, Reproducibility Track) , pp. 3059--3069
bib / paper / code

BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents


Chen, Z.*, Ma, X.*, Zhuang, S.*, Nie, P., Zou, K., Sharifymoghaddam, S., Liu, A., Green, J., Patel, K., Meng, R., Su, M., Li, Y., Hong, H., Shi, X., Liu, X., Oyarhoseini, H., Thakur, N., Zhang, C., Gao, L., Chen, W., & Lin, J.
Annual Meeting of the Association for Computational Linguistics (ACL 2026) , pp. 22349--22370
bib / paper / website / code

RankLLM: A Python Package for Reranking with LLMs


Sharifymoghaddam, S., Pradeep, R., Slavescu, A., Nguyen, R., Xu, A., Chen, Z., Zhang, Y., Chen, Y., Xian, J., & Lin, J.
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2025)
bib / paper / code

UniRAG: Universal Retrieval Augmentation for Large Vision Language Models.


Sharifymoghaddam, S.*, Upadhyay, S.*, Chen W., & Lin, J.
Findings of the Association for Computational Linguistics (NAACL 2025) , pp. 2026--2039
bib / paper / code

Search Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM Responses


Sharifymoghaddam, S.*, Upadhyay, S.*, Thakur, N.*, Pradeep, R., & Lin, J.
International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR 2026) , pp. 403--413
bib / paper / code

Ragnarök: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track.


Pradeep, R., Thakur, N., Sharifymoghaddam, S., Zhang, E., Nguyen, R., Campos, D., Craswell, N., & Lin, J.
European Conference on Information Retrieval (ECIR 2025) , pp. 132--148
bib / paper / code

RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!


Pradeep, R., Sharifymoghaddam, S., & Lin, J.
Preprint (arXiv 2023)
bib / paper / code

RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models.


Pradeep, R.*, Sharifymoghaddam, S.*, & Lin, J.
Preprint (arXiv 2023)
bib / paper / code