Siyu Yuan

I'm a fourth-year Ph.D. student at Fudan University. I am advised by Prof. Deqing Yang and Prof. Yanghua Xiao at Knowledge Work Lab. Previously, I received my Bachelor's degree from Fudan University in 2021. I am a recipient of several awards, including China National Scholarship for Doctoral Students (博士生国家奖学金), ACL 2023 Outstanding Paper Award, Outstanding Graduate Student (优秀毕业生) in Shanghai, and Outstanding Student Pacemaker of Fudan University (复旦大学优秀学生标兵).

Email / Resume / Google Scholar / Github

Research: Human-like Autonomous Language Agents

I am devoted to making language agents have human-like cognitive abilities and aligning autonomous generative agents with human cognition, aiming to create agents that saying, thinking, and acting humanly with language:

Planning and Reasoning: Focus on equipping generative agents with human-level planning and reasoning capabilities through reflection, multi-agent collaboration, tool usage, and etc., as in Agent-R | EvoAgent | EasyTool | CoScript.
Cognitive Modeling: Explore cognitive knowledge (such as Analogy, Idiom, Pun and Role-playing) in generative agents to enable them to generate responses that align better with human cognition, as in SCUA | CROSS | InCharacter.
Knowledge Acquisition: Excavate cognitive knowledge based on generative agents to construct rich knowledge resources that can be effectively utilized, as in AnalogyKB | IdiomKB | KPCE.

Selected Publications

A full list of publications is here. (* indicates equal contribution.)

	Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training Siyu Yuan, Zehui Chen, Zhiheng Xi, Junjie Ye, Zhengyin Du, Jiecao Chen arXiv, 2025 (Huggingface Daily Paper Top-1) GitHub
	EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, Deqing Yang NAACL, 2025 Homepage / GitHub
	EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Ren Kan, Dongsheng Li, Deqing Yang NAACL, 2025 (23.6k+ GitHub Stars, JARVIS project) GitHub
	TaskBench: Benchmarking Large Language Models for Task Automation Yongliang Shen, Kaitao Song, Xu Tan, Wenqi Zhang, Kan Ren, Siyu Yuan, Weiming Lu, Dongsheng Li, Yueting Zhuang Neurips, 2024 (23.6k+ GitHub Stars, JARVIS project)* GitHub
	From Persona to Personalization: A Survey on Role-Playing Language Agents 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 TMLR*, 2024 arXiv
	Distilling Script Knowledge from Large Language Models for Constrained Language Planning Siyu Yuan, Jiangjie Chen, Ziquan Fu, Xuyang Ge, Soham Shah, Charles Jankowski, Yanghua Xiao, Deqing Yang ACL, 2023 (Outstanding Paper Award) GitHub

Internship

ByteDance Seed Team - Research Intern(Sep. 2024 - Present)
Manager: Jiangjie Chen
Microsoft Research Lab Asia - Research Intern (Sep. 2023 - Jun. 2024)
Manager: Kaitao Song
ByteDance AI Lab - Research Intern (Jan. 2023 - Jun. 2023)
Manager: Jiaze Chen
Brain Technologies Inc - Research Intern (Jun. 2022 - Sep. 2022)
Manager: Charles Jankowski

Selected Awards

National Scholarship, China, 2023-2024
Outstanding Paper Award, ACL, 2023
Outstanding Graduate Student, Shanghai, 2021
Outstanding Student Pacemaker, Fudan University, 2020
National Scholarship, China, 2017-2018

🐶 🍦 🤖