Aili Chen

Aili Chen

Ph.D Student

Fudan University

Biography

Hi, I'm Aili Chen (ι™ˆθ‰Ύεˆ©). I am a first-year Ph.D. student at Fudan University, advised by Prof. Yanghua Xiao at Knowledge Work Lab. Previously, I received my Bachelor's degree from Fudan University in 2024. I have interest in Large Language Model, especially in reasoning models and autonomous agents:

Interests
  • Reasoning & Planning
  • Language Agent
  • LLM Personalization
  • Music, Photography, and Travel
Education

  • Ph.D. in CS, 2024 - 2029 (expected)

    Fudan University

  • B.S. in Information Security, 2020 - 2024

    Fudan University

News

  • July. 2025: πŸ‡¦πŸ‡Ή Attending ACL 2025@Vienna! I will present DEEPER! Looking forward to meeting everyone!

  • Jun. 2025: πŸ”” Introducing Minimax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism!

  • May. 2025: πŸ”” Check out Enigmata! A complete pipeline for advancing logical reasoning in LLMs, from data generation β†’ verification β†’ RLVR training β†’ evaluation.

  • May. 2025: πŸ”” Check out ARIA! we propose ARIA, a method that Aggregates Rewards in Intention space to enable efficient and effective language Agents training.

  • May. 2025: πŸ”” Check out ARM! LLMs often suffer from "overthinking" - excessive reasoning that wastes computational resources. ARM introduces adaptive reasoning formats and multiple modes to optimize token usage while maintaining performance.

  • May. 2025: πŸ”” Check out SynLogic! A comprehensive logical reasoning data synthesis framework that generates diverse, verifiable reasoning data at scale for learning logical reasoning and beyond.

  • May. 2025: πŸŽ‰ Our paper DEEPER is accepted to ACL 2025!

  • Mar. 2025: πŸŽ‰ Our paper SelfGoal is accepted to NAACL 2025!

  • Jan. 2025: πŸŽ‰ Our paper Think Thrice Before You Act is accepted to ICLR 2025!

  • Sep. 2024: πŸŽ‰ Our survey paper on role-playing agents is accepted to TMLR!

    • Aug. 2024: πŸ”” Check out TravelAgent! We introduce an LLM-powered travel planning system that generates rational comprehensive and personalized itineraries.

Experience

 
 
 
 
 
ByteDance AI Lab
Research Intern
MiniMax
Jan 2025 – Present Shanghai, China
Work on LLMs' reasoning capabilities, language agents and multi-turn rl.
 
 
 
 
 
Alibaba Group
Research Intern
Alibaba Group
Mar 2024 – Feb 2025 Hangzhou, China
Research on personalized LLM-based agent and RAG.
 
 
 
 
 
Meituan
Information Security Engineer Intern
Meituan
Jul 2023 – Sep 2023 Beijing, China
Information Security Division - Mobility Security Research Department.

Awards

Outstanding Graduate of Shanghai
Fudan University Jun 2024
Top 1%
National Second Prize
Chinese National College Student Information Security Competition Aug 2023
Top 10%
Meritorious Award
American College Student Mathematical Modeling Contest May 2023
Top 6%
Huawei Scholarship
Huawei Nov 2022
Top 3%
Outstanding Student Leader of Fudan University
Fudan University Oct 2021
Top 2%
Outstanding Communist Youth League Member of Fudan University
Fudan University Oct 2021
Top 5%

Featured Publications

Aili Chen, Aonian Li, Bangwei Gong, Binyang Jiang, Bo Fei, Bo Yang, Boji Shan, Changqing Yu, Chao Wang, Cheng Zhu, Chengjun Xiao, Chengyu Du, Chi Zhang, Chu Qiao, Chunhao Zhang, Chunhui Du, et al.
June, 2025 Technical Report
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism.
PDF Cite Code Model Dataset
Jiangjie Chen, Qianyu He, Siyu Yuan, Aili Chen, Zhicheng Cai, Weinan Dai, Hongli Yu, Qiying Yu, Xuefeng Li, Jiaze Chen, Hao Zhou, Mingxuan Wang
May, 2025 Technical Report
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

We introduce Enigmata, the first comprehensive suite tailored for improving LLMs with puzzle reasoning skills.
PDF Cite Dataset Project Code Model
Aili Chen, Chengyu Du, Jiangjie Chen, Jinghan Xu, Yikai Zhang, Siyu Yuan, Zulong Chen, Liangyue Li, Yanghua Xiao
February, 2025 ACL 2025
DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling
DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling

We introduce DEEPER, a novel approach for dynamic persona modeling that enables continual persona optimization through iterative reinforcement learning framework.
PDF Cite Code Model Data
Ruihan Yang, Yikai Zhang, Aili Chen, Xintao Wang, Siyu Yuan, Jiangjie Chen, Deqing Yang, Yanghua Xiao
June, 2025 arXiv preprint
ARIA: Training Language Agents with Intention-Driven Reward Aggregation
ARIA: Training Language Agents with Intention-Driven Reward Aggregation

We propose ARIA, a method that Aggregates Rewards in Intention space to enable efficient and effective language Agents training.
PDF Cite Project
Siye Wu, Jian Xie, Yikai Zhang, Aili Chen, Kai Zhang, Yu Su, Yanghua Xiao
May, 2025 arXiv preprint
ARM: Adaptive Reasoning Model
ARM: Adaptive Reasoning Model

LLMs often suffer from "overthinking" - excessive reasoning that wastes computational resources. ARM introduces adaptive reasoning formats and multiple modes to optimize token usage while maintaining performance.
PDF Cite Project
Aili Chen, Xuyang Ge, Ziquan Fu, Yanghua Xiao, Jiangjie Chen
September, 2024 Preprint
TravelAgent: An AI Assistant for Personalized Travel Planning
TravelAgent: An AI Assistant for Personalized Travel Planning

We introduce TravelAgent, an LLM-powered travel planning system that generates rational, comprehensive, and personalized itineraries through four modules, demonstrating effectiveness in dynamic scenarios.
PDF Cite Demo

Recent Publications

Quickly discover relevant content by filtering publications.
MiniMax: Aili Chen, Aonian Li, Bangwei Gong, Binyang Jiang, Bo Fei, Bo Yang, Boji Shan, Changqing Yu, Chao Wang, Cheng Zhu, Chengjun Xiao, Chengyu Du, Chi Zhang, Chu Qiao, Chunhao Zhang, Chunhui Du, et al. (2025). MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention. Preprint.

PDF Cite

Jiangjie Chen, Qianyu He, Siyu Yuan, Aili Chen, Zhicheng Cai, Weinan Dai, Hongli Yu, Qiying Yu, Xuefeng Li, Jiaze Chen, Hao Zhou, Mingxuan Wang (2025). Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles. Technical Report.

PDF Cite Dataset Project Code Model

Ruihan Yang, Yikai Zhang, Aili Chen, Xintao Wang, Siyu Yuan, Jiangjie Chen, Deqing Yang, Yanghua Xiao (2025). ARIA: Training Language Agents with Intention-Driven Reward Aggregation. Preprint.

PDF Cite

Siye Wu, Jian Xie, Yikai Zhang, Aili Chen, Kai Zhang, Yu Su, Yanghua Xiao (2025). ARM: Adaptive Reasoning Model. Preprint.

PDF Cite

Aili Chen, Chengyu Du, Jiangjie Chen, Jinghan Xu, Yikai Zhang, Siyu Yuan, Zulong Chen, Liangyue Li, Yanghua Xiao (2025). DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling. The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025).

PDF Cite Code

See all publications

Visitors