About Me
I am Yiding Wang, a senior undergraduate student at Peking University, majoring in Artificial Intelligence. Currently, I am a member of Mμ Lab, advised by Prof. Muhan Zhang. My research in Mμ Lab focuses on Large Language Models (LLMs) Reasoning and Parameter-Efficient Fine-Tuning (PEFT).
Previously, I conducted research in Beijing Institute for General Artificial Intelligence (BIGAI), developing human-like social agents under the mentorship of Prof. Fangwei Zhong. I am also fortunate to visit Prof. Yu Meng and Prof. Jiaxuan You’s Lab and collaborate with them as an intern.
Research Interests:
- The revolution leads to the next generation of foundational models.
- Adapting foundation models more effectively to the field of agents, aiming to construct agents with general intelligence (e.g., social interaction, adaptive decision-making, long-horizon planning).
News
- 25/10/28: Introducing Multi-Agent Evolve and Law in Silico!
- 25/10/06: Introducing DeSA, a two-stage training framework for search agents!
- 25/09/25: I’m honored to receive the Xiaomi Scholarship!
- 25/09/23：Our paper Law in Silico: Simulating Legal Society with LLM-Based Agents has been accepted by NeurIPS 2025 LAW Workshop, the paper will be released soon!
- 25/09/19: One paper accepted by NeurIPS 2025 Dataset and Benchmark Track!
- 25/08/21: Our paper: HD-PiSSA has been accepted to EMNLP 2025 Main Conference！ (ORAL)
- 25/07/12: I’m honored to receive the Tong Class Dean’s Scholarship!
- 25/06/12: I’m honored to be 1/30 of SenseTime Scholarship 2025!
- 25/01/23: Our paper: Simulating Human-like Activities with Desire-driven Autonomy has been accepted by ICLR’2025!
- 24/12/06: Our team (BIGAI NLCo) ranked #9 in the NeurIPS 2024 Concordia Contest!
Preprint Papers
ArXiv
Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
Yiding Wang, Zhepei Wei, Xinyu Zhu, Yu Meng.
ArXiv
Multi-Agent Evolve: LLM Self-Improve Through Co-Evolution
Multi-Agent Evolve: LLM Self-Improve Through Co-Evolution
Yixing Chen*, Yiding Wang*, Siqi Zhu, Haofei Yu, Tao Feng, Muhan Zhang, Mostofa Patwary, Jiaxuan You.
NeurIPS LAW Workshop
Law in Silico: Simulating Legal Society with LLM-Based Agents
Law in Silico: Simulating Legal Society with LLM-Based Agents
Yiding Wang*, Yuxuan Chen*, Fanxu Meng, Xifan Chen, Xiaolei Yang, Muhan Zhang.
Selected Publications
EMNLP 2025 Oral
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation
Yiding Wang*, Fauxu Meng*, Xuefeng Zhang, Fan Jiang, Pingzhi Tang, Muhan Zhang.
ICLR 2025
Simulating Human-like Daily Activities with Desire-driven Autonomy
Simulating Human-like Daily Activities with Desire-driven Autonomy
Yiding Wang*, Yuxuan Chen*, Fangwei Zhong, Long Ma, Yizhou Wang.
Service
- AAAI 2026 (Social Impact Track) Reviewer
- ICLR 2026 Reviewer
Awards
- Xiaomi Scholarship (¥5,000 RMB) - 2025
- Tong Class Dean’s Scholarship (¥10,000 RMB) — 2025
- SenseTime Scholarship 2025 (¥20,000 RMB) — 2025 (Only 30 winners nationwide)
- Peking University Scholarship (¥4,000 RMB) — 2024
- Peking University Practice and Public Welfare Award — 2024
- Yanchuang Capital Scholarship (¥8,000 RMB) — 2023
- Peking University Excellent Student Award — 2023