🎓 About Me

I am Haotian Luo. I received my B.Eng. in Software Engineering from Sichuan University in 2026.

My research interests include large language models, and LLM agents. Recently I focus on long-horizon and autonomous agents.

📖 Education

  • 2022 - 2026: B.Eng. in Software Engineering (Honoured Bachelor), Sichuan University
  • 2021 - 2022: B.Eng. in Electronic Engineering, Sichuan University

💼 Experience

  • 2026.03 - 2026.07: LLM Research Intern, Qwen Team, Alibaba Group
  • 2025.11 - 2026.03: LLM Research Intern, Meituan (Talent Program)
  • 2025.07 - 2025.10: LLM Research Intern, DiDi Global

📜 News

2026.06: Received my B.Eng. in Software Engineering from Sichuan University.
2026.05: Four papers accepted to ICML 2026.
2026.04: Four papers accepted to ACL 2026.
2025.09: Two papers accepted to NeurIPS 2025.

📝 Publications

* denotes equal contribution.

UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
Haotian Luo, Huaisong Zhang, Xuelin Zhang, Haoyu Wang, Zeyu Qin, Wenjie Lu, Guozheng Ma, Haiying He, Yingsha Xie, Qiyang Zhou, Zixuan Hu, Hongze Mi, Yibo Wang, Naiqiang Tan, Hong Chen, Yi R. Fung, Chun Yuan, Li Shen
ICML 2026
[Paper] [Code]
MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline
Huanjin Yao, Qixiang Yin, Min Yang, Ziwang Zhao, Yibo Wang, Haotian Luo, Jingyi Zhang, Jiaxing Huang
ICML 2026
[Paper] [Code]
Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution
Hongze Mi, Yibo Feng, Wenjie Lu, Song Cao, Jinyuan Li, Yanming Li, Xuelin Zhang, Haotian Luo, Songyang Peng, He Cui, Tengfei Tian, Jun Fang, Hua Chai, Naiqiang Tan
ICML 2026
[Paper]
Language-based Trial and Error Falls Behind in the Era of Experience
Haoyu Wang, Guozheng Ma, Shugang Cui, Yilun Kong, Haotian Luo, Li Shen, Mengya Gao, Yichao Wu, Xiaogang Wang, Dacheng Tao
ICML 2026
[Paper]
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, Dacheng Tao
ACL 2026
[Paper] [Code]
D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents
Hongze Mi, Yibo Feng, Wenjie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Naiqiang Tan, Gang Pan
ACL 2026
[Paper]
Ada-R1: From Long-CoT to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
Haotian Luo, Haiying He, Yibo Wang, Jinluan Yang, Rui Liu, Naiqiang Tan, Xiaochun Cao, Dacheng Tao, Li Shen
NeurIPS 2025
[Paper]
Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
Yibo Wang, Tiansheng Huang, Li Shen, Huanjin Yao, Haotian Luo, Rui Liu, Naiqiang Tan, Jiaxing Huang, Dacheng Tao
NeurIPS 2025
[Paper] [Code]
R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
Yibo Wang*, Haotian Luo*, Li Shen, Huanjin Yao, Tiansheng Huang, Rui Liu, Naiqiang Tan, Jiaxing Huang, Kai Zhang, Dacheng Tao
NeurIPS 2025 FoRLM Workshop
[Paper] [Code]
Vector-Quantized Prompt Learning for Paraphrase Generation
Haotian Luo, Yixin Liu, Peidong Liu, Xianggen Liu
EMNLP 2023
[Paper]

📧 Contact

Email: haotianluo2002@gmail.com