Xiaoshuai Song (宋晓帅)  Ph.D. Student Gaoling School of Artificial Intelligence (GSAI) Renmin University of China (RUC) Beijing, China, 100872. Email: songxiaoshuai@ruc.edu.cn [Google Scholar]

Biography

I am a first-year Ph.D. student of RUC-NLPIR Lab in the Gaoling School of Artificial Intelligence, Renmin University of China (RUC), advised by Prof. Zhicheng Dou and Prof. Ji-Rong Wen. Previously, I received my M.S. degree from the School of Artificial Intelligence, Beijing University of Posts and Telecommunications in June 2025, advised by Prof. Weiran Xu.

My current research interests center on Large Language Model (LLM) agents, specifically focusing on (1) Web Information Acquisition, and (2) General Tool Use.

News

• [2026-01] We propose EnvScaler, an automated framework for scalable tool-interaction environments via programmatic synthesis! See more details.
• [2025-05] Two paper has been accepted by ACL2025 main!
• [2025-01] One paper has been accepted by WWW2025, and two papers has been accepted by ICLR2025!
• [2024-06] We propose CS-Bench, the first benchmark dedicated to evaluating the performance of LLMs in computer science! See more details.

Experiences

Academia

• [2025.9 - Now] Ph.D. student at Renmin University of China
• [2022.9 - 2025.6] M.S. at Beijing University of Posts and Telecommunications
• [2018.9 - 2022.6] B.S. at Beijing University of Posts and Telecommunications

Industry

• [2024.7 - 2024.12] Alibaba, Taobao & TMall - Future Life Lab, LLM Algorithm Research Intern.
• [2023.7 - 2024.6] SenseTime, Research Institute - NLP, Algorithm Research Intern.

Preprints

• EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
  Xiaoshuai Song, Haofei Chang, Guanting Dong, Yutao Zhu, Zhicheng Dou, Ji-Rong Wen
  Arxiv 26.01. [paper] [github]

Publications

(* denotes equal contributions)
-2025-

• ProgCo: Program Helps Self-Correction of Large Language Models
  Xiaoshuai Song, Yanan Wu, Weixun Wang, Jiaheng Liu, Wenbo Su, Bo Zheng
  ACL2025 Main. [paper]

• We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
  Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma GongQue, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Yifan Zhang, Xiao Zong, Yida Xu, Muxi Diao, Zhimin Bao, Chen Li, Honggang Zhang
  ACL2025 Main. [paper] [website]

• CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
  Xiaoshuai Song, Muxi Diao, Guanting Dong, Zhengyang Wang, Yujia Fu, Runqi Qiao, Zhexu Wang, Dayuan Fu, Huangxuan Wu, Bin Liang, Weihao Zeng, Yejie Wang, Zhuoma GongQue, Jianing Yu, Qiuna Tan, Weiran Xu
  ICLR2025. [paper] [website]

• MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
  Pei Wang, Yanan Wu, Zekun Wang, Jiaheng Liu, Xiaoshuai Song, Zhongyuan Peng, Ken Deng, Chenchen Zhang, Jiakai Wang, Junran Peng, Ge Zhang, Hangyu Guo, Zhaoxiang Zhang, Wenbo Su, Bo Zheng
  ICLR2025. [paper]

• Assessing and Post-Processing Black Box Large Language Models for Knowledge Editing
  Xiaoshuai Song, Zhengyang Wang, Keqing He, Guanting Dong, Jinxu Zhao, Weiran Xu
  WWW2025 Oral. [paper]

-2024-

• Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
  Guanting Dong, Xiaoshuai Song, Yutao Zhu, Runqi Qiao, Zhicheng Dou, Ji-Rong Wen
  AAAI2025. [paper] [website]

• Faceptor: A Generalist Model for Face Perception
  Lixiong Qin, Mei Wang, Xuannan Liu, Yuhang Zhang, Wei Deng, Xiaoshuai Song, Weiran Xu, and Weihong Deng
  ECCV2024 Oral. [paper]

• Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
  Pei Wang, Keqing He, Yejie Wang, Xiaoshuai Song, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
  LERC-COLING 2024. [paper]

• Noise-BERT: A Unified Perturbation-robust Framework With Noise Alignment Pre-training For Noisy Slot Filing Task
  Jinxu Zhao, Guanting Dong, Yueyan Qiu, Tingfeng Hui, Xiaoshuai Song, Daichi Guo, Weiran Xu
  ICASSP 2024. [paper]

-2023-

• Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT
  Xiaoshuai Song, Keqing He, Pei Wang, Guanting Dong, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
  EMNLP2023 Main. [paper]

• Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition
  Xiaoshuai Song, Yutao Mou, Keqing He, Yueyan Qiu, Pei Wang, Weiran Xu
  EMNLP2023 Findings. [paper]

• APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
  Pei Wang, Keqing He, Yutao Mou, Xiaoshuai Song, Yanan Wu, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
  EMNLP2023 Findings. [paper]

• Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
  Yutao Mou, Xiaoshuai Song*, Keqing He, Chen Zeng, Pei Wang, Jingang Wang, Yunsen Xian, Weiran Xu
  ACL2023 Main. [paper]

Honors & Awards

• Excellent Master's Thesis Award (Top 1%), BUPT. 2025
• National Scholarship (Top 1%), Ministry of Education. 2024
• Outstanding Master Students (Top 5%), BUPT. 2023, 2024
• Excellent First-class Scholarship for Master Students, BUPT. 2022, 2023
• Chinese College Student Mathematics Competition (Preliminary round), First Prize, 2022.01
• MathorCup University Mathematical Modeling Challenge, Second Prize, 2021.03
• The Mathematical Contest in Modeling, Honorable Mention, 2020.4

Last updated: 2026.01