Long-horizon agents, from pre-training to evaluation.

Keyu Li (李克钰), second-year Ph.D. student at Shanghai Jiao Tong University and Shanghai Innovation Institute, advised by Dequan Wang and Pengfei Liu. Working on LLM continual pre-training & mid-training, agentic RL, multi-agent systems, and frontier AI evaluation.

Now a research intern at Tencent Youtu Lab, building CPT / mid-training data and RL recipes for coding agents. Previously at GAIR Lab, where I led AgencyBench and DatasetResearch. Heavy daily user of Claude Code and Codex.

Resume (PDF) → chlorophyll@sjtu.edu.cn WeChat · 13370856505

News

May 2026Joined Tencent Youtu Lab as a research intern, working on LLM CPT / mid-training and agentic RL.
Apr 2026AgencyBench accepted to the ACL 2026 Main Conference.
Mar 2026Two papers accepted to ICLR 2026: Aligned Agents, Biased Swarm and InnovatorBench.
Sep 2025Released LIMI: Less is More for Agency.
Aug 2025Released DatasetResearch, a benchmark for demand-driven dataset discovery.

Publications Google Scholar →

AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts ACL 2026 main

Keyu Li, Junhao Shi, Yang Xiao, Mohan Jiang, Jie Sun, Yunze Wu, Dayuan Fu, Shijie Xia, Xiaojie Cai, Tianze Xu, Weiye Si, Wenjie Li, Dequan Wang, Pengfei Liu

first authorpaper code arXiv:2601.11044
Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems ICLR 2026

Keyu Li, Jin Gao, Dequan Wang

first authorcode
InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research ICLR 2026

Yunze Wu, Dayuan Fu, Weiye Si, Zhen Huang, Mohan Jiang, Keyu Li, Shijie Xia, Jie Sun, Tianze Xu, Xiangkun Hu, Pengrui Lu, Xiaojie Cai, Lyumanshan Ye, Wenhong Zhu, Yang Xiao, Pengfei Liu

paper code arXiv:2510.27598
daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently arXiv 2026

Mohan Jiang, Dayuan Fu, Junhao Shi, Ji Zeng, Weiye Si, Keyu Li, Xuefeng Li, Yang Xiao, Wenjie Li, Dequan Wang, Pengfei Liu

paper code arXiv:2602.02619
DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery arXiv 2025

Keyu Li, Mohan Jiang, Dayuan Fu, Yunze Wu, Xiangkun Hu, Dequan Wang, Pengfei Liu

first authorpaper code arXiv:2508.06960
LIMI: Less is More for Agency arXiv 2025

Yang Xiao, Mohan Jiang, Jie Sun, Keyu Li, Jifan Lin, Yumin Zhuang, Ji Zeng, Shijie Xia, Qishuo Hua, Xuefeng Li, Xiaojie Cai, Tongyu Wang, Yue Zhang, Liming Liu, Xia Wu, Jinlong Hou, Yuan Cheng, Wenjie Li, Xiang Wang, Dequan Wang, Pengfei Liu

co-first authorpaper code arXiv:2509.17567
Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training arXiv 2025

Dayuan Fu, Yunze Wu, Xiaojie Cai, Lyumanshan Ye, Shijie Xia, Zhen Huang, Weiye Si, Tianze Xu, Jie Sun, Keyu Li, Mohan Jiang, Junfei Wang, Qishuo Hua, Pengrui Lu, Yang Xiao, Pengfei Liu

paper arXiv:2510.27630
KAN-Mixer: Kolmogorov-Arnold Networks for Gene Expression Prediction in Plant Species ECCV 2024 Workshops

Jin Gao, Juntu Zhao, Keyu Li, Dequan Wang

paper

Experience

Tencent Youtu Lab · Research Intern 2026.05 – now
CPT / mid-training data for coding agents, agentic RL and on-policy distillation.
Shanghai Innovation Institute · GAIR Lab · Research Intern 2025.05 – 2026.05
Post-training and evaluation of LLM agents with Prof. Pengfei Liu: AgencyBench, DatasetResearch, LIMI.
Soochow Securities · Fintech · Quant Research Intern 2024.06 – 2024.09
Deep-learning factor mining on Level-2 market data (CNN / RNN / Transformer / KAN).

Education

Shanghai Jiao Tong University · Ph.D., Computer Science and Technology 2024 – 2029
Joint program with Shanghai Innovation Institute. Advisors: Dequan Wang, Pengfei Liu.
Shanghai Jiao Tong University · B.S., Mathematics and Applied Mathematics 2020 – 2024
GPA 4.03 / 4.3, rank 4 / 45. Shanghai Outstanding Graduate, Guo Chenchen Scholarship. Thesis: Towards Visualizing and Understanding Bayesian Flow Networks.

Visitors details →

Thanks for stopping by. Readers so far, by country: