CV
Curriculum vitae of Junteng Liu.
Contact Information
| Name | Junteng Liu |
| Professional Title | Third-year Ph.D. Student |
| jliugi@connect.ust.hk |
Professional Summary
Third-year Ph.D. student at HKUST NLP Group studying recursive self-improvement (RSI) and coding agents for long-horizon AI development, with verifiable feedback and reinforcement learning for logical reasoning, search, and inference systems.
Experience
-
2026.04 - 2026.09 Cupertino, USA
Research Scientist Intern
Apple MLR
- Mentored by Yizhe Zhang and Ruixiang Zhang.
- Developed and publicly released RSI-Inference (first author), a benchmark of 37 real-world tasks evaluating whether coding agents can autonomously develop and maintain vLLM and SGLang on H100 and B200 GPUs.
- Day-0 model support (10 tasks): Built tasks for integrating previously unsupported models, evaluated through correctness and serving-feature checks.
- Inference optimization (20 tasks): Built tasks requiring source-code changes to improve serving throughput under fixed deployment settings.
- Bug fix (7 tasks): Built tasks requiring agents to identify and repair performance regressions.
- Sonnet-5.5 and Opus-5.5 ranked first and second overall, achieving 1.68× and 1.48× geometric-mean speedups across the 27 optimization and bug-fix tasks, but only 26.7% and 13.3% pass@1 on Day-0 Model Support, respectively. DeepSeek-V4.1-Flash achieved 0.0% support pass@1 and 1.24× speedup.
-
2025.02 - 2026.02 Shanghai, China
Research Intern
MiniMax
- Core contributor to MiniMax-M1 and MiniMax-M2.
- Logical reasoning RL: Developed SynLogic (first author, NeurIPS 2025), synthesizing rule-verifiable data across 35 logical task types and training reasoning models. SynLogic-32B outperformed DeepSeek-R1-Distill-Qwen-32B on BBEH (25.5% vs. 19.2%). This data and RL work contributed to MiniMax-M1.
- Search-agent RL: Developed WebExplorer (first author) and conducted RL training experiments for long-horizon web agents, using challenging search tasks synthesized through web exploration and query evolution. WebExplorer-8B surpassed WebSailor-72B on BrowseComp-en/zh (Avg@4: 15.7% vs. 12.0% / 32.0% vs. 30.1%). The data was used in MiniMax-M2 and formed the basis for subsequent MiniMax-M3 search-data improvements.
-
2024.06 - 2024.09 Shanghai, China
Research Intern
Tencent WXG
- Mentored by Zifei Shan.
- Investigated vision-encoder bottlenecks in VLM chart understanding and trained improved encoders with contrastive learning. First-author paper: On the Perception Bottleneck of VLMs for Chart Understanding (Findings of EMNLP 2025).
-
2023.06 - 2023.12 Shanghai, China
Research Intern
Shanghai AI Lab
- Mentored by Prof. Yu Cheng.
- Investigated a universal truthfulness hyperplane using probes trained on 40+ datasets; found that data diversity improves cross-dataset generalization. First-author paper: On the Universal Truthfulness Hyperplane Inside LLMs (EMNLP 2024).
Research Questions
- How can we train agents to do ultra-long-horizon RSI or AI4AI development?
- Beyond coding agents, what other domains can we explore?
Education
-
2024 - Present Hong Kong
Ph.D.
Hong Kong University of Science and Technology
Computer Science
- HKUST NLP Group; advisor: Prof. Junxian He.
-
2020 - 2024 Shanghai, China
B.Eng.
Shanghai Jiao Tong University
Automation (IEEE Honor Class)
Publications
-
2026 RSI-Inference: A Long-Horizon Benchmark for Self-Improving Inference Systems
Benchmark 2026
Junteng Liu, Richard He Bai, Huangjie Zheng, Yizhe Zhang, Ruixiang Zhang. Code. GitHub stars: 100+ (Oct 22, 2026).
-
2026 The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
arXiv 2026
MiniMax Team (including Junteng Liu as a core contributor). Code.
-
2026 The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
ICLR 2026
Junlong Li, Wenshuo Zhao, Jian Zhao, Weihao Zeng, Haoze Wu, Xiaochen Wang, Rui Ge, Yuxuan Cao, Yuzhen Huang, Wei Liu, Junteng Liu, Zhaochen Su, Yiyang Guo, Fan Zhou, Lueyang Zhang, Juan Michelini, Xingyao Wang, Xiang Yue, Shuyan Zhou, Graham Neubig, Junxian He. Code. GitHub stars: 500+ (Oct 22, 2026). Reported in official model evaluations by OpenAI, Anthropic, Google DeepMind (Gemini), Moonshot AI (Kimi), DeepSeek, and MiniMax.
-
2026 Learn to Reason Efficiently with Adaptive Length-Based Reward Shaping
ICLR 2026
Wei Liu, Ruochen Zhou, Yiyun Deng, Yuzhen Huang, Junteng Liu, et al. Code.
-
2026 DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
ICML 2026
Aili Chen, Chi Zhang, Junteng Liu, et al. Code.
-
2025 WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
arXiv 2025
Junteng Liu*, Yunji Li*, Chi Zhang, Jingyang Li, Aili Chen, Ke Ji, Weiyu Cheng, Zijia Wu, Chengyu Du, Qidi Xu, Jiayuan Song, Zhengmao Zhu, Wenhu Chen, Pengyu Zhao, Junxian He. Code. Citations: 80+ · GitHub stars: 120+ (Oct 22, 2026).
-
2025 MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
arXiv 2025
MiniMax Team (including Junteng Liu as a core contributor). Code.
-
2025 SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
NeurIPS 2025
Junteng Liu, Yuanxiang Fan, Zhuo Jiang, Han Ding, Yongyi Hu, Chi Zhang, Yiqi Shi, Shitong Weng, Aili Chen, Shiqi Chen, Yunan Huang, Mozhi Zhang, Pengyu Zhao, Junjie Yan, Junxian He. Code. GitHub stars: 200+ (Oct 22, 2026).
-
2025 On the Perception Bottleneck of VLMs for Chart Understanding
Findings of EMNLP 2025
Junteng Liu, Weihao Zeng, Xiwen Zhang, Yijun Wang, Zifei Shan, Junxian He. Code.
-
2024 On the Universal Truthfulness Hyperplane Inside LLMs
EMNLP 2024
Junteng Liu, Shiqi Chen, Yu Cheng, Junxian He. Code.
-
2024 In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
ICML 2024
Shiqi Chen, Miao Xiong, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, Junxian He. Code.
-
2023 Composing Parameter-Efficient Modules with Arithmetic Operation
NeurIPS 2023
Jinghan Zhang, Shiqi Chen, Junteng Liu, Junxian He. Code. Citations: 260+ (Oct 22, 2026).
-
2023 C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
NeurIPS 2023
Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu, Junlei Zhang, Jinghan Zhang, Tangjun Su, Junteng Liu, Chuancheng Lv, Yikai Zhang, Jiayi Lei, Yao Fu, Maosong Sun, Junxian He. Code. Citations: 1,000+ · GitHub stars: 1.8k+ (Oct 22, 2026).
Awards
-
2020–2024 Zhiyuan Honor Scholarship
Shanghai Jiao Tong University