Leonard Li (Shang'ao Li, 李尚敖)

News

• June 2026Pinned

  Recruiting research interns. I'm helping a group I work with at LMU Munich find research interns. The group works on reinforcement learning and LLM / web agents (a recent paper accepted at ICLR 2026) and is continuing RL work on vertical agent applications. Remote; ample compute provided for RL / LLM work.

  Looking for: students able to commit full-time (≥40 h/week) or part-time (≥20 h/week), with substantial hands-on RL experience — you know the theory — and able to build agent systems independently. Strong contributors typically earn co-authorship on resulting work.

  Start: rolling — begin anytime; budget ~1 week to ramp up. Interested? Email me at leo@lsamc.website with your CV and a brief description of a relevant project you've built (a GitHub repo link is welcome) — RL / agent ideally, though strong project experience in other areas is also welcome. Happy to chat first.

• August 2026

  📄 Our paper QuoteBench: How Matched Scores Can Hide Command-Path Failures is now on arXiv (with Yao Zhang, Volker Tresp, and Yuanyuan Yang) — showing that matched execution scores for LLM coding agents can hide failures on the command path, so evals must report the generation contract, execution path, and validator, not just the score. Project site.

• July 2026

  🔨 Introducing Human-Crafted Software — a badge and spec for projects you designed and wrote yourself, with no AI generating or editing the committed source code. Proudly human-made — a small counterpoint to vibe-coding.

Research Interests

I work on enhancing reasoning capabilities in AI systems through principled integration of symbolic and neural methods. My research explores how formal reasoning, neuro-symbolic architectures, and interactive verification can improve reliability and interpretability in language models and autonomous agents.

Keywords: Autonomous Agents · Reinforcement Learning & Reward Modeling · ML Mechanics · Formal Methods · Continual Learning · Quantum Computing (secondary)

Education

Ph.D. in Computer Engineering, Stony Brook University
Aug 2026 - Present

B.Sc. in Information and Computing Sciences (Computer Science Track)
School of Computer Science, Nanjing University
Sept. 2022 - June 2026 · GPA: 4.60/5.00 (Rank: 3/25)

Research Experience

• Microsoft Research Asia (MSRA) · Apr 2026 - Present
  Research Intern, Advisor: Ziyu Zhou
• Ludwig Maximilian University of Munich · Nov 2025 - Present
  Research Intern, Advisor: Dr. Yao Zhang
• KRistal Group, Nanjing University · Oct 2025 - Present
  Research Intern, Advisor: Prof. YiZheng Zhao
• Independent Research · Jul 2025 - Present
  Research Intern, Advisor: Dr. Zhen Han
• ScaleML Lab, UIUC · Apr - Jun 2025
  Research Intern, Advisor: Prof. Tong Zhang
• Huawei 2012 Labs · Jul - Sept 2025
  Research Intern, Supervisor: JianFeng Gui
• QUEST Lab, NC State University · Jul - Nov 2024
  Research Intern, Advisor: Prof. Yuan Liu

Selected Honors

• National Scholarship (Top 0.2% nationwide), Ministry of Education of China, 2025
• First Prize (National Champion), HITCTF 2025 Cybersecurity Competition
• National First Prize, Entropy Cup Cryptography Challenge (CACR), 2025
• Outstanding Student Pacesetter (university-level), Nanjing University, 2024-2025
• Special Scholarship for Fundamental Subjects, First Prize (twice), 2023-2025