Tsinghua University · Computer Science
Agent & LLM Research
I study the capability boundaries of agents on real-world tasks, and how reasoning, feedback, and self-improvement in large language models can help agents take on more complex, long-horizon work.
About
AI is moving from answering questions to completing tasks. My research began with reasoning and recommendation in large language models, and now spans Coding Agents, engineering optimization, and algorithm design. I study how to measure agent capabilities in environments close to real work, and how planning, feedback, and self-improvement become transferable abilities.
Selected Publications
Selected work on agent evaluation, long-horizon tasks, and LLM reasoning.
arXiv · 2026
Introduces a cross-platform recommendation market led by User Agents, showing that broader product access does not automatically translate into effective exposure. With user feedback, positively promotional pitches fall from 73–78% to 36–41%.
arXiv · 2026
A long-horizon Coding Agent benchmark for whole-repository technology-stack migration, combining migration audits, functional tests, and adversarial validation. Only 5.4% of 520 runs passed every check.
arXiv · 2026
R2Rank maps chain-of-thought reasoning over a user–candidate pair to a relevance score, then optimizes end to end with a Plackett–Luce distribution and NDCG-based reinforcement learning to reduce positional bias in LLM ranking.
arXiv · 2026
A benchmark for self-evolving agents on real engineering optimization tasks, measuring whether agents can improve engineering artifacts within a fixed interaction budget through a propose–execute–evaluate–iterate loop and executable feedback.
arXiv · 2026
A benchmark for LLM agents’ algorithm-design ability: agents explore and rewrite training algorithms in an open environment, then train and evaluate from scratch in an independent environment to separate algorithmic innovation from tuning.
* Co-first authors or Core Contributors.
Beyond Research
Advanced curriculum reform and teaching feedback for the age of AI.
The only third-year Computer Science volunteer representative serving at the commemorative event.
Organized graduate-school sharing sessions and maintained student support services.
Participated in supervision and feedback on student affairs.
Organized joint theme activities across three schools; the class Youth League branch was recognized as a university-level A-grade branch.