Siyu Yuan

I'm a final-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 2025 Outstanding Paper Award, 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).

👀 I am currently on the job market! Actively seeking roles in building agentic intelligence. Open to full-time positions and research collaborations in generative AI. Let's connect!

Email / Resume / Google Scholar / Github

Research: Planning and Reasoning in Language Models

I am dedicated to advancing fundamental planning and reasoning capabilities in language models, with a particular focus on building reasoning models and autonomous agents:

Reasoning Models: Exploring and advancing research on incentivizing and understanding complex reasoning and planning capabilities in large language models. Key approaches include reinforcement learning and iterative self-reflection, as in Seed1.5-Thinking | ThinkDial | Enigmata | CoScript.
Autonomous Agents: Developing agentic intelligence - autonomous systems capable of making decisions and executing plans with minimal human intervention. This includes investigating their interactions in real-world environments, emphasizing efficient tool utilization and powerful multi-agent collaboration, as in Kimi-K2-Thinking |Kimi-K2-Instruct-0905 | EasyTool | EvoAgent | Agent-R.

News

2025-11: Introduce Kimi-K2-Thinking, our best open-source thinking model! I'm honored to have contributed to its Agentic Reasoning Capabilities and welcome to try it!
2025-09: Five paper is accepted to NeurIPS 2025! Four of them are accepted as Spotlight (3.2%)!
2025-09: Introduce Kimi-K2-Instruct-0905, the most capable version of Kimi K2! I'm honored to have contributed to its Tool-Integrated Reasoning and to have collaborated with such an great team!
2025-08: Introduce ThinkDial, the first open-recipe end-to-end framework that successfully implements gpt-oss-style controllable reasoning through discrete operational modes.
2025-08: Five paper is accepted to EMNLP 2025!
2025-07: Our paper about History Analogy got an Outstanding Paper Award in ACL 2025 (Top 0.3%)!
2025-07: Start Student Researcher Internship at Moonshot AI RL Team!
2025-05: Introducing Enigmata, a Full-Stack Recipe for advancing logical reasoning in LLMs! Enigmata offers a complete pipeline to systematically enhance the logic reasoning skills of LLMs.
2025-05: Five papers are accepted to ACL 2025!
2025-05: One paper is accepted to ICML 2025!
2025-04: Introduce Seed1.5-Thinking, a reasoning model that capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks! I'm honored to have contributed to its logical reasoning capabilities and to have collaborated with such an outstanding team!
2025-01: Introduce Agent-R, a novel framework designed to enable LLM-based agents to perform on-the-fly reflection and self-improvement in the iteractive environment!
2025-01: One paper is accepted to CHI 2025!
2025-01: Four papers are accepted to NAACL 2025 Main Conference!
2024-09: Start Student Researcher Internship at Bytedance Seed!
2024-09: TaskBench is accepted to NeurIPS 2024!
2024-09: Three papers are accepted to EMNLP 2024 Main Conference!
2024-05: Four papers are accepted to ACL 2024!
2023-09: Start Student Researcher Internship at Microsoft Research Asia
2023-06: Coscript got an Outstanding Paper Award in ACL 2023 (Top 1%)!
2023-01: Start Student Researcher Internship at Bytedance AI Lab!

Selected Publications

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

Kimi K2: Open Agentic Intelligence
Siyu Yuan (co-author), contributed to Tool-Integrated Reasoning for Kimi Kimi-K2-Instruct-0905
Technical Report, 2025. (Huggingface Download: 41k+)
Homepage

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
Qianyu He*, Siyu Yuan*, Xuefeng Li, Mingxuan Wang, Jiangjie Chen
Technical Report, 2025.

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Jiangjie Chen*, Qianyu He*, Siyu Yuan*, Aili Chen*, Zhicheng Cai, Weinan Dai, Hongli Yu, Qiying Yu, Xuefeng Li, Jiaze Chen, Hao Zhou, Mingxuan Wang
NeurIPS Spotlight (3.2%), 2025. Core Contributor.
Homepage

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
Siyu Yuan (co-author), contributed to Logic Reasoning Capabilities for Seed1.5-Thinking
Technical Report, 2025. (700+ GitHub Stars)
GitHub

	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. (100+ GitHub Stars, 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. (100+ GitHub Stars) 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
	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

Moonshot AI RL Team - Research Intern(July 2025 - Present)
Manager: Dehao Zhang
ByteDance Seed Team - Research Intern(Sep. 2024 - June 2025)
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

Outstanding Paper Award, ACL, 2025
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

🐶 🍦 🤖