Hansi Zeng

PhD student, University of Massachusetts at Amherst

Joined

March 2022

Names

Hansi Zeng (Preferred)

Emails

****@cs.umass.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

University of Massachusetts at Amherst (umass.edu)

2021 – 2026

Advisors, Relations & Conflicts

PhD Advisor

Hamed Zamani

2021 – 2025

Expertise

Agentic Reinforcement Learning

2025 – Present

Information Retrieval

2020 – Present

Publications

Enhancing LLM Reasoning with Retrieval-Augmented Logical Chains and Test-Time Adaptation
Junda Wang, Zonghai Yao, Hansi Zeng, Zhichao Yang, Hamed Zamani, hong yu
- Submitted to ICLR 2026
- Readers: Everyone
When Scale is Fixed: Revisiting Pre-training Indicators for LLM Fine-tuning Performance
Hansi Zeng, Kai Hui, Honglei Zhuang, Zhen Qin, Zhenrui Yue, Hamed Zamani, Dana Alon
- Submitted to ICLR 2026
- Readers: Everyone
SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
Jiacheng Lin, Zhongruo Wang, Kun Qian, Tian Wang, Arvind Srinivasan, Hansi Zeng, Ruochen Jiao, Xie Zhou, Jiri Gesi, Dakuo Wang, Yufan Guo, Kai Zhong, Weiqi Zhang, sujay sanghavi, Changyou Chen, Hyokun Yun, Lihong Li
- ICLR 2026 Poster
- Readers: Everyone
SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
Jiacheng Lin, Zhongruo Wang, Kun Qian, Tian Wang, Arvind Srinivasan, Hansi Zeng, Ruochen Jiao, Xie Zhou, Jiri Gesi, Dakuo Wang, Yufan Guo, Kai Zhong, Weiqi Zhang, Sujay Sanghavi, Changyou Chen, Hyokun Yun, Lihong Li
- CoRR 2025
- Readers: Everyone
ATEB: Rethinking Advanced NLP Tasks in an Information Retrieval Setting
Simeng Han, Frank Palma Gomez, Tu Vu, Zefei Li, Daniel Cer, Hansi Zeng, Chris Tar, Arman Cohan, Gustavo Hernandez Abrego
- KnowFM @ ACL 2025
- Readers: Everyone
Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?
Hansi Zeng, Kai Hui, Honglei Zhuang, Zhen Qin, Zhenrui Yue, Hamed Zamani, Dana Alon
- CoRR 2025
- Readers: Everyone
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan O Arik, Dong Wang, Hamed Zamani, Jiawei Han
- COLM 2025
- Readers: Everyone
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Bowen Jin, Hansi Zeng, Zhenrui Yue, Dong Wang, Hamed Zamani, Jiawei Han
- CoRR 2025
- Readers: Everyone
Scaling Sparse and Dense Retrieval in Decoder-Only LLMs
Hansi Zeng, Julian Killingback, Hamed Zamani
- CoRR 2025
- Readers: Everyone
Hypencoder: Hypernetworks for Information Retrieval
Julian Killingback, Hansi Zeng, Hamed Zamani
- CoRR 2025
- Readers: Everyone

View all 42 publications

Co-Authors

View all 82 co-authors