$*$ indicates equal contribution, and $^\dagger$ indicates corresponding author.

2026

Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training Preprint. Paper · Code

Xinyu Che$^*$, Hang Yan$^*$, Yanchen Liu$^*$, Haochen Liu, Ruifeng Li, Anran Shi, Heng Wang, Jun Liu$^\dagger$.

OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions Preprint. Paper · Code

Fangzhi Xu$^*$, Hang Yan$^*$, Qiushi Sun$^*$, Jinyang Wu, Zixian Huang, Muye Huang, Jingyang Gong, Zichen Ding, Kanzhi Cheng, Yian Wang, Xinyu Che, Zeyi Sun, Jian Zhang, Zhangyue Yin, Haoran Luo, Xuanjing Huang, Ben Kao, Jun Liu, Qika Lin$^\dagger$.

TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents EMNLP 2026 (Main). Paper · Code

Hang Yan$^*$, Xinyu Che$^*$, Fangzhi Xu$^{*\dagger}$, Qiushi Sun, Zichen Ding, Kanzhi Cheng, Jian Zhang, Tao Qin, Jun Liu, Qika Lin$^\dagger$.