Dehai Min   闵德海

👋 I am a second-year CS Ph.D. student (Aug. 2025–) at University of Illinois Chicago (UIC), advised by Prof. Philip S. Yu (Fellow of ACM, IEEE and AAAS). In Summer 2026, I was a Research Scientist Intern at ByteDance (San Jose) Doubao Enterprise Team, where I worked on Agent Long-horizon Trace Evaluation and Agent Environment Reconstruction & Synthesis. I received my M.S. from Southeast University, advised by Prof. Guilin Qi, and my B.S. from Hefei University. I am deeply grateful for the previous guidance from Prof. Chenyu You from Stony Brook University.

My current research interests include:

1. Agent Long-horizon Trace Evaluation & Agent Environment Reconstruction & Synthesis
2. Retrieval-Augmented Generation (RAG) & Deep Research
3. Efficient and Trustworthy LLMs

Previously, during my master's studies, I worked on LLMs with heterogeneous data (text, graphs, and tables).

I am always open to research discussions and exploring internship opportunities — feel free to reach out!

🎉 News

• [2026.09] New paper released: TraceDance — An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces. Paper and project website are now available! 📄 Paper / 🌐 Website
• [2026.08] Two papers accepted: TSRouter by COLM 2026 (📄 Paper / 📦 Code) & EpiQAL by EMNLP 2026! 🎉
• [2026.06] New paper: Stop When Reasoning Converges — Semantic-Preserving Early Exit for Reasoning Models (PUMA). 📄 Paper / 📦 Code / 🤗 Models & Datasets
• [2026.06] New paper (co-first): CorVer — Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering. 📄 Paper / 📦 Code
• [2026.05] Moved to San Jose, CA (Bay Area) to start as a Research Scientist Intern @ ByteDance, working with the Doubao Agent Team at AML / Volcano Engine-Ark.
• [2026.05] Two papers (Latent Thoughts Tuning & MVI-Bench) accepted by ICML 2026! 🎉
• [2026.04] One paper (QuCo-RAG) accepted by ACL Findings 2026! 📄 Paper / 📦 Code / Covered by 🔥 新智元. Thanks to Dr. Cheng for her guidance!
• [2026.02] New paper on latent reasoning: Latent Thoughts Tuning — Bridging Context and Reasoning with Fused Information in Latent Tokens. 📄 Paper / 📦 Code
• [2025.12] Selected as Outstanding Reviewer of 2024–2025 for IEEE TNNLS! 📦 Certificate
• [2025.12] New paper released: MVI-Bench — Evaluating Robustness to Misleading Visual Inputs in LVLMs. 📄 Paper / 📦 Code
• [2025.08] Moved to Chicago 🇺🇸.
• [2025.01] 🎉 One paper (UniHGKR) accepted by NAACL 2025 as Oral, with the highest meta-review score of 5! 📦 Code / 🤗 Models & Datasets
• [2024.12] One paper accepted by AAAI 2025!

🎓 Education

University of Illinois Chicago , Ph.D. , 08/2025 - present

Southeast University , M.S. , 09/2022 - 06/2025

Hefei University , B.S. , 09/2017 - 06/2022

🧑‍🏫 Internship

ByteDance (TikTok) , 05/2026 - 08/2026
Research Scientist Intern , San Jose, California
Doubao Enterprise Agent Team at AML / Volcano Engine-Ark.
Data flywheel from deployed API traffic back into Doubao Seed model training.

📝 Publications and Preprints

(* denotes equal contribution.)

First-author Publications

• Dehai Min, Daoan Zhang, Yiming Zeng, Huayi Zhang, Ziyi Chen, Yan Zhang, Qinbo Bai, Mengyuan Chao et al. TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces Preprint
  📄 Paper / 🌐 Website

• Dehai Min*, Giovanni Vaccarino*, Huiyi Chen, Yongliang Wu, Gal Yona, Lu Cheng. Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Preprint
  📄 Paper / 📦 Code / 🤗 Models & Datasets /

• Dehai Min, Kailin Zhang, Tongtong Wu, Lu Cheng. QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation ACL Findings 2026
  📄 Paper / 📦 Code /

• Dehai Min, Zhiyang Xu, Guilin Qi, Lifu Huang, and Chenyu You. UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers NAACL 2025, Oral Highest Meta-Review Score: 5
  📄 Paper / 📦 Code / 🤗 Models & Datasets

• Dehai Min*, Nan Hu*, Rihui Jin, Nuo Lin, Jiaoyan Chen, Yongrui Chen, Yu Li et al. Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data NAACL 2024, Oral
  📄 Paper / 🎤 Slides

• Yiming Tan*, Dehai Min*, Yu Li, Wenbo Li, Nan Hu, Yongrui Chen, and Guilin Qi. Can ChatGPT replace traditional KBQA models? An in-depth analysis of the question answering performance of the GPT LLM family ISWC 2023, Oral 367 Citations
  📄 Paper / 📦 Code / 🎤 Slides

• Shicheng Fan*, Haochang Hao*, Dehai Min*, Weihao Liu, Philip S. Yu, Lu Cheng. Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering Preprint
  📄 Paper / 📦 Code

Selected Collaborative Publications

• Fangxu Yu, Tao Feng, Dehai Min, Lu Cheng, Ge Liu, Tianyi Zhou. TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning COLM 2026
  📄 Paper / 📦 Code

• Weihao Liu, Dehai Min, Lu Cheng. Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens ICML 2026
  📄 Paper / 📦 Code

• Mingyang Wei, Dehai Min, Zewen Liu, Yuzhang Xie, Guanchen Wu, Carl Yang, Max S.Y. Lau, Qi He, Lu Cheng, Wei Jin. EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering for Enhanced Alignment and Reasoning EMNLP 2026

• Huiyi Chen, Jiawei Peng, Dehai Min, Changchang Sun, Kaijie Chen, Yan Yan, Xu Yang, Lu Cheng. MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs ICML 2026
  📦 Code

🏅 Competitions

( I was an active participant in programming competitions during my undergraduate years. )

• ACM-ICPC (International Collegiate Programming Contest) , Asian Regional Contest (including all participating universities in mainland China), 2019-2020, 2 times Silver Medal. individual / team
• CCPC-Finals (China Collegiate Programming Contest National Finals), 2019, 21st place, Silver Medal
• Anhui Province Collegiate Programming Contest, First Prize (2 times, 2019, 2020), Champion🏆 (1 time, 2020)
• Codeforces Rating: 2108 (Master), link

👨‍💻 Academic Services

• Outstanding Reviewer of 2024–2025, IEEE TNNLS 📦 Certificate

• Reviewer of ACL 2025/2026, EMNLP 2025/2026, ICML 2026, NeurIPS 2026, AAAI 2027

• Reviewer of IEEE Transactions on Neural Networks and Learning Systems (TNNLS)