Author

MohammadHossein Rezaei

Observed name: Rezaei, MohammadHossein

Institution: University of Arizona

Observed institution: University of Arizona

OpenAlex ID: A5102422296

MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers

2026 · Bandi, Chaithanya, Dumitru, Razvan-Gabriel, et al. · arXiv (Cornell University) · 71

Online Rubrics Elicitation from Pairwise Comparisons

2025 · Rezaei, MohammadHossein, Vacareanu, Robert, et al. · arXiv (Cornell University) · 41

Reward Hacking in Rubric-Based Reinforcement Learning

2026 · Mahmoud, Anas, Rezaei, MohammadHossein, et al. · arXiv (Cornell University) · 36

Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers

2026 · Rezaei, MohammadHossein, Mahmoud, Anas, et al. · arXiv (Cornell University) · 17

Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR

2026 · Tyagi, Utkarsh, Guo, Xingang, et al. · arXiv (Cornell University) · 13

SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution

2026 · Raghavendra, Mohit, Dan, Soham, et al. · arXiv (Cornell University) · 12

RSI-Forge: From Research Papers to Environments for Recursive Self-Improvement

2026 · Wang, Renxiong, Yi, Darvin, et al. · arXiv (Cornell University) · 3

Paraphrasing in Affirmative Terms Improves Negation Understanding

2024 · MohammadHossein Rezaei, Eduardo Blanco · Proceedings of the conference - Association for Computational Linguistics. Meeting · 3

CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data

2026 · Gupta, Vipul, Wang, Zihao, et al. · arXiv (Cornell University) · 2

Making Language Models Robust Against Negation

2025 · MohammadHossein Rezaei, Eduardo Blanco · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 2

Evidence-First Agentic Verification

2026 · Sanayei, Reza, Dumitru, Razvan-Gabriel, et al. · arXiv (Cornell University) · 1

Interpreting Indirect Answers to Yes-No Questions in Multiple Languages

2023 · Zijie Wang, Md Hossain, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 1

Predicting Privileged Information Effectiveness for On-Policy Self-Distillation

2026 · Zou, Kaijian, Penaloza, Emiliano, et al. · arXiv (Cornell University)

Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding

2026 · Association for Computational Linguistics 2026, Blanco, Eduardo, et al. · Underline Science Inc.

Interpreting Indirect Answers to Yes-No Questions in Multiple Languages

2023 · Wang, Zijie, Hossain, Md Mosharaf, et al. · arXiv (Cornell University)

Works count: 15

Citation count: 202

H-index: 6

I10-index: 6