Yucheng Shi

史淯城
Lila Sciences — Member of Technical Staff (MTS)
Ph.D. in Computer Science, University of Georgia
Advised by Prof. Ninghao Liu

I work on self-evolving agents and scientific discovery at Lila Sciences. My research explores how agents learn from interaction and improve through experience. My work spans agent reinforcement learning, long-horizon evaluation, executable environment synthesis, and asynchronous post-training.

Yucheng Shi

News

Nov 2026Joined Lila Sciences as a Member of Technical Staff (MTS), working on self-evolving agents and scientific discovery.
Aug 2026Released Recursive Synthesis for Long-Horizon Terminal Tasks — 37,484 verified tasks across 15 rounds at about $0.05 per task. Paper · Blog arXiv
Jul 2026Released Stale but Stable — a staleness-adaptive trust region for stabilizing asynchronous RL. Paper · Blog arXiv
Jul 2026Released Long-Horizon-Terminal-Bench — 46 long-horizon terminal tasks with dense, subtask-level grading. Paper arXiv
Jan 2026Successfully defended my Ph.D. dissertation at the University of Georgia. Ph.D.

Experience

Lila Sciences Nov 2026 – Present
Member of Technical Staff (MTS)
  • Self-evolving Agents & Scientific Discovery.
Tencent Hunyuan LLM Frontier, Seattle 2026
Research Scientist
  • Agent RL and self-evolving AI.
Netflix Sep – Dec 2025
ML Research Intern  ·  Dr. Ying Li, Dr. Yu Wang
  • Content recommendation with large language models.
Tencent AI Lab, Seattle May – Aug 2025
Research Scientist Intern  ·  Dr. Wenhao Yu
  • MobileGUI-RL: online RL for mobile GUI agent automation.
  • Multimodal AI for mobile UI understanding.
Harvard Medical School May – Sep 2024
Student Researcher  ·  Dr. Xiang Li
  • Post-trained LLaMA-3 70B on 6.5M+ radiology reports.
  • Built SearchRAG for medical question answering.

Selected Publications full list →

Recursive Synthesis for Long-Horizon Terminal Tasks
Zhongzhi Li*, Yucheng Shi*, Zongxia Li*, Ruhan Wang, Anhao Li, Zixun Huang, Junyao Yang, Lei Ke, Ninghao Liu, Haitao Mi, Leowei Liang
arXiv 2026 · Project lead · Paper · Blog · Data & Models
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning
Junyao Yang, Yucheng Shi, Zongxia Li, Zhongzhi Li, Ruhan Wang, Xiangxin Zhou, Kishan Panaganti, Haitao Mi, Leowei Liang
arXiv 2026 · Project lead · Paper · Blog · Code
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ninghao Liu, Lichao Sun, Haotao Mi, LeoweiLiang
arXiv 2026 · Paper · Project · Code · Leaderboard
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
Yucheng Shi, Zhenwen Liang, Kishan Panaganti, Dian Yu, Wenhao Yu, Haitao Mi
Preprint 2026
MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
Yucheng Shi*, Wenhao Yu*, Zaitang Li, Yonglin Wang, Hongming Zhang, Ninghao Liu, Haitao Mi, Dong Yu
arXiv 2025 · Paper
Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
Yucheng Shi, Quanzheng Li, Jin Sun, Xiang Li, Ninghao Liu
ICLR 2025 · Paper · Code · Model · 5k+ HF downloads
CORTEX: Concept-Oriented Token Explanation in Vector-Quantized Generative Models
Tianze Yang*, Yucheng Shi*, Mengnan Du, Xuansheng Wu, Qiaoyu Tan, Jin Sun, Ninghao Liu
ICML 2025 · Paper · Code
Black-box Backdoor Defense via Zero-shot Image Purification
Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Jin Sun, Ninghao Liu
NeurIPS 2023 · Paper · Code
MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering
Yucheng Shi*, Shaochen Xu*, Tianze Yang*, Zhengliang Liu, Tianming Liu, Quanzheng Li, Xiang Li, Ninghao Liu
AMIA 2024 · Paper · Code · Distinguished Paper Award

Contact

The best way to reach me is email: mailofsyc@gmail.com. I am always glad to talk with people working on self-evolving agents, scientific discovery, and agent reinforcement learning.