Research on self-improving agents, LLM-based simulation, repository-scale reasoning, and agent evaluation.
Google Scholar2026
Findings of ACL
Yiding Wang*, Yuxuan Chen*, Fanxu Meng, Xifan Chen, Xiaolei Yang, Muhan Zhang
An LLM-agent framework for simulating legal societies through individual and institutional decision-making.
2026
arXiv preprint
Zhonghang Li*, Zongwei Li*, Yuxuan Chen, Han Shi, Jiawei Li, Jierun Chen, Haoli Bai, Chao Huang
Structural scouting and cost-aware context construction for repository-scale code reasoning.
2025
arXiv preprint
Tianyu Fan, Yuhao Yang, Yangqin Jiang, Yifei Zhang, Yuxuan Chen, Chao Huang
A live benchmark for evaluating autonomous LLM agents across stocks and cryptocurrency markets.
2025
NeurIPS Datasets & Benchmarks
Chandler Smith, Marwa Abdulhai, Manfred Díaz, [54 authors omitted], Yuxuan Chen, [28 authors omitted]
An evaluation of how LLM agents generalize cooperative behavior across unseen partners and social scenarios.
2025
ICLR
Yiding Wang*, Yuxuan Chen*, Fangwei Zhong, Long Ma, Yizhou Wang
A desire-driven autonomous agent that proposes and selects activities using a dynamic value system inspired by human needs.
* Equal contribution.