Hai Ye's Homepage

Hai Ye

AI Research Scientist @ MiroMind | LLM agents · long-horizon reasoning · agentic foundation models

[Google Scholar]

Bio:

Hi! I am Hai Ye. I am an AI Research Scientist at Apodex and MiroMind since 2025. I obtained my Ph.D. degree from the School of Computing at the National University of Singapore, supported by the AISG Ph.D. Fellowship, and worked with Prof. Ng Hwee Tou. I obtained my B.Eng. from Beihang University, Beijing, China.

My current research focuses on building reliable LLM agents and agentic foundation models for long-horizon reasoning, and deep research.

Research Interests:

Large Language Models, Agentic Foundation Models, Long-horizon Reasoning (e.g., STEM, Math), Data Synthesis.

Highlights:

Building agentic foundation models for STEM reasoning and deep research.
Contributed to the MiroThinker series at MiroMind.
Research experience across LLM alignment, test-time adaptation, robust QA, and multilingual/domain adaptation.

Contact: hye.me [at] outlook [dot] com

Projects

MiroThinker Series [v1.7] [v1.5] [v1.0]
Contributed to the MiroThinker series at MiroMind, a line of agentic foundation models for long-horizon reasoning and deep research.

Selected Papers

(* indicates equal contribution)

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
MiroMind Team, Hai Ye, et al.
In arXiv preprint, 2603.15726.
[paper]
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroMind Team, Hai Ye, et al.
In arXiv preprint, 2511.11793.
[paper]
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
Yibo Wang, Lei Wang, Yue Deng, Keming Wu, Yao Xiao, Huanjin Yao, Liwei Kang, Hai Ye, Yongcheng Jing, Lidong Bing
In arXiv preprint, 2601.09688.
[paper]
MiroMind-M1: An Open-source Advancement in Mathematical Reasoning via Context-aware Multi-stage Policy Optimization
Xingxuan Li*, Yao Xiao*, Dianwen Ng*, Hai Ye*, Yue Deng*, Xiang Lin*, Bin Wang*, Zhanfeng Mo, Chong Zhang, Yueyi Zhang, Zonglin Yang, Ruilin Li, Lei Lei, Shihao Xu, Han Zhao, Weiling Chen, Feng Ji, Lidong Bing
In arXiv preprint, 2507.14683.
[paper]
Enhancing Writing Assistance with Rationale via Self-Training for Improved Alignment
Hannan Cao, Hai Ye, Hwee Tou Ng
In Findings of the Association for Computational Linguistics: ACL, 2025, Long paper.
Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
Yao Xiao, Hai Ye, Linyao Chen, Hwee Tou Ng, Lidong Bing, Xiaoli Li, Roy Ka-wei Lee
In Proceedings of the Association for Computational Linguistics (ACL), 2025, Long paper.
Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration
Hai Ye, Mingbao Lin, Hwee Tou Ng, Shuicheng Yan
In arXiv preprint, 2412.17061.
[paper]
Self-Judge: Selective Instruction Following with Alignment Self-Evaluation
Hai Ye, Hwee Tou Ng
In arXiv preprint, 2409.00935.
[paper]
Preference-Guided Reflective Sampling for Aligning Language Models
Hai Ye, Hwee Tou Ng
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024, Long paper.
[paper] [code] [website]
Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Hai Ye, Qizhe Xie, Hwee Tou Ng
In Proceedings of the Association for Computational Linguistics (ACL), 2023, Long paper.
[paper] [code]
Beware of Model Collapse! Fast and Stable Test-time Adaptation for Robust Question Answering
Yi Su, Yixin Ji, Juntao Li, Hai Ye, Min Zhang
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023, Long paper.
Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models
Yixin Ji, Jikai Wang, Juntao Li, Hai Ye, Min Zhang
In Findings of the Association for Computational Linguistics: EMNLP, 2023, Long paper.
Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
Hai Ye, Yuyang Ding, Juntao Li, Hwee Tou Ng
In Findings of the Association for Computational Linguistics: EMNLP, 2022, Long paper.
[paper] [code]
On the Robustness of Question Rewriting Systems to Questions of Varying Hardness
Hai Ye, Hwee Tou Ng, Wenjuan Han
In Proceedings of the Association for Computational Linguistics (ACL), 2022, Long paper.
[paper]
On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation
Ruidan He*, Linlin Liu*, Hai Ye*, Qingyu Tan, Bosheng Ding, Liying Cheng, David Low, Lidong Bing, Luo Si
In Proceedings of the Association for Computational Linguistics (ACL), 2021, Long paper.
[paper]
Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training
Hai Ye, Qingyu Tan, Ruidan He, Juntao Li, Hwee Tou Ng, Lidong Bing
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Long paper.
[paper] [code]
Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model
Juntao Li, Ruidan He, Hai Ye, Hwee Tou Ng, Lidong Bing, Rui Yan
In Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI), 2020.
[paper]
Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
Hai Ye, Wenjie Li, Lu Wang
In Proceedings of the Association for Computational Linguistics (ACL), 2019, Long paper.
[paper] [poster]
Semi-Supervised Learning for Neural Keyphrase Generation
Hai Ye, Lu Wang
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018, Long paper.
[paper]
Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions
Hai Ye*, Xin Jiang*, Zhunchen Luo*, Wenhan Chao
In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2018, Long paper, Oral.
[paper] [data] [slides]
Jointly Extracting Relations with Class Ties via Effective Deep Ranking
Hai Ye, Wenhan Chao, Zhunchen Luo, Zhoujun Li
In Proceedings of the Association for Computational Linguistics (ACL), 2017, Long paper.
[paper] [code]

Academic Services

Area Chair: ACL Rolling Review
Reviewer: ARR, ACL, NAACL, EMNLP, COLING, COLM 2024, NeurIPS 2024-2025, ICLR 2024-2025, ICML 2025
Volunteer: NAACL 2018

Last update: 2026