Yikai Zhang

About

I am Yikai Zhang, a fourth-year Ph.D. student in the School of Computer Science at Fudan University, advised by Prof. Yanghua Xiao. My work focuses on language agents and agentic models, especially reasoning and planning, post-training, and benchmark design for LLM-based agents. I am based in Shanghai and open to collaborations on autonomous agents and LLMs. Feel free to reach me by email.

Experience

Knowledge Works Lab, Fudan University

2022 - Present

Ph.D. Student

Ph.D. Advisor: Yanghua Xiao
Topic: Autonomous Agents

Institute for AI Industry Research, Tsinghua University

Mar. 2025 - Present

Research Intern

Advisor: Hao Zhou
Topic: LLMs for Scientific Discovery, especially in biology

ByteDance AI Lab

Mar. 2024 - Jan. 2025

Research Intern

Advisors: Rong Ye and Peng Sun
Topic: Language Agents for Social Deduction Games (e.g., Werewolf)

Publications

(^* indicates equal contribution)

Sirui Xia^*, Yikai Zhang^*, Aili Chen, Siye Wu, Siyu Yuan, Yanghua Xiao

Ruihan Yang^*, Yikai Zhang^*, Aili Chen, Xintao Wang, Jiangjie Chen, Siyu Yuan, Deqing Yang, Yanghua Xiao

Yikai Zhang, Rong Ye, Siyu Yuan, Jiangjie Chen, Jian Xie, Yanghua Xiao

Rong Ye^*, Yongxin Zhang^*, Yikai Zhang, Haoyu Kuang, Zhongyu Wei, Peng Sun

Ruihan Yang, Jiangjie Chen, Yikai Zhang, Siyu Yuan, Aili Chen, Kyle Richardson, Yanghua Xiao, Deqing Yang

Jian Xie, Kexun Zhang, Jiangjie Chen, Siyu Yuan, Kai Zhang, Yikai Zhang, Lei Li, Yanghua Xiao

Siye Wu, Jian Xie, Yikai Zhang, Aili Chen, Kai Zhang, Yu Su, Yanghua Xiao

Yikai Zhang, Siyu Yuan, Caiyu Hu, Kyle Richardson, Yanghua Xiao, Jiangjie Chen

Siye Wu, Jian Xie, Yikai Zhang, Yanghua Xiao

Yang Liu, Enxi Wang, Yufei Gao, Weixin Zhang, Bo Wang, Zhiyuan Zeng, Yikai Zhang, Yining Zheng, Xipeng Qiu

Qianyu He, Junting Lu, Yikai Zhang, Siyu Yuan, Xiaojun Meng, Jiansheng Wei, Jiaqing Liang, Yanghua Xiao

Sirui Xia, Aili Chen, Xintao Wang, Tinghui Zhu, Yikai Zhang, Jiangjie Chen, Yanghua Xiao

Lida Chen, Dong Xu, Chenxin An, Xintao Wang, Yikai Zhang, Jiangjie Chen, Zujie Liang, Feng Wei, Jiaqing Liang, Yanghua Xiao, Wei Wang

Ruihan Yang, Fanghua Ye, Jian Li, Siyu Yuan, Yikai Zhang, Zhaopeng Tu, Xiaolong Li, Deqing Yang

Aili Chen, Chengyu Du, Jiangjie Chen, Jinghan Xu, Yikai Zhang, Siyu Yuan, Zulong Chen, Liangyue Li, Yanghua Xiao

Jiangjie Chen^*, Xintao Wang^*, Rui Xu^*, Siyu Yuan^*, Yikai Zhang^*, Wei Shi^*, Jian Xie^*, Shuang Li, Ruihan Yang, Tinghui Zhu, Aili Chen, Nianqi Li, Lida Chen, Caiyu Hu, Siye Wu, Scott Ren, Ziquan Fu, Yanghua Xiao

Caiyu Hu, Yikai Zhang, Tinghui Zhu, Yiwei Ye, Yanghua Xiao

Yikai Zhang, Qianyu He, Xintao Wang, Siyu Yuan, Jiaqing Liang, Yanghua Xiao

Qianyu He, Yikai Zhang, Jiaqing Liang, Yuncheng Huang, Yanghua Xiao, Yunwen Chen

Zhouhong Gu, Zihan Li, Lin Zhang, Zhuozhi Xiong, Haoning Ye, Yikai Zhang, Wenhao Huang, Xiaoxuan Zhu, Qianyu He, Rui Xu, Sihang Jiang, Shusen Wang, Zili Wang, Hongwei Feng, Zhixu Li, Yanghua Xiao

Yikai Zhang

About

Experience

Knowledge Works Lab, Fudan University

Institute for AI Industry Research, Tsinghua University

ByteDance AI Lab

Publications

Selected Publications

From AI Assistant to AI Scientist: Autonomous Discovery of LLM-RL Algorithms with LLM Agents [PDF]

ARIA: Training Language Agents with Intention-driven Reward Aggregation [PDF]

Enhancing Language Agent Strategic Reasoning through Self-Play in Adversarial Games [PDF]

Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game [PDF]

SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals [PDF]

Revealing the Barriers of Language Agents in Planning [PDF]

ARM: Adaptive Reasoning Model [PDF]

TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation [PDF]

Other Publications

CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning [PDF]

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping [PDF]

Metaphor Reasoning is Meta-reasoning [PDF]

Can LLMs Learn to Map the World from Local Descriptions? [PDF]

PowerAttention: Exponentially Scaling of Receptive Fields for Effective Sparse Attention [PDF]

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement [PDF]

DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling [PDF]

From persona to personalization: A survey on role-playing language agents [PDF]

MCITEBENCH: A Benchmark for Multimodal Citation Text Generation in MLLMs [PDF]

Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models [PDF]

HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation [PDF]

DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? [PDF]