YIXIA LI Ph.D.

Google Scholar
liyixia@me.com
https://liyixia.me

About

I am a final-year Ph.D. student at Southern University of Science and Technology (SUSTech), supervised by Dr. Guanhua Chen. I am currently a research intern with Tencent Hunyuan Team. Prior to this, I interned at Microsoft Research Asia and Huawei.
Research Interests
News

Research Experience

Tencent | Hunyuan Team
2026.05 - Now
  • Post-training of the HY3 & HY4 models
  • Agentic Learning
Microsoft Research Asia | GenAI Group
2025.06 - 2026.05
  • Agentic Learning
  • Efficient Large Language Models
PolyU | SMART Lab
2022.08 - 2023.07
  • Social Media Opinion Polling
  • Cantonese Medical Dialogue System
Huawei
2022.06 - 2022.08
  • Extractive Document Q&A
  • Knowledge-enhanced Dialogue System
[Company Name]
[Location]
Mentor: Name of Mentor
[Start Date] - [End Date]
  • [Description]
  • [Description]

Education

Southern University of Science and Technology
Shenzhen, China
Ph.D. in Mathematics
2023 - 2027
  • Supervisor: Dr. Guanhua Chen.
  • Research Area: Agentic Learning, LLM Post-training, Efficient Methods in LLMs.
The Hong Kong Polytechnic University
Hong Kong, China
M.Sc. in Computer Science with Distinction
2021 - 2023
  • Rank: Top 5%, GPA: 3.8/4.0.
Guangzhou University
Guangzhou, China
B.Sc. in Statistics
2017 - 2021
  • Rank: Top 5%, GPA: 3.7/4.0.
[University Name]
[Location]
[Degree and Major]
[Start Year] - [End Year]
  • [Detail 1]
  • [Detail 2]

Publications

* equal contribution

2026

Theory of Agent: The Science of Internalization and Externalization for LLM-based Agents
  • Zihao Cheng*, Yixia Li*, Shengbin Yue*, Yuheng Lu*, Yuli Qiu, Yanzhi Tian, Haohuinan Zhang, Cheng Qian, Hongru WANG, Guanhua Chen, Zeming Liu, Yuhang Guo, zhongyu wei, Ke Gu, Liang Li, Jeff Z. Pan, Amos Storkey, Yunhong Wang, Haifeng Wang
  • Under Review, 2026 [paper][code]
Bridging the Agent-World Gap: Text World Models for LLM-based Agents
  • Yixia Li, Hongru Wang, Peng Lai, Zhiwen Ruan, He Zhu, Youxin Zhu, Ganlong Zhao, Minda Hu, Yun Chen, Sibei Yang, Peng Li, Jeff Z. Pan, Jia Pan, Guanhua Chen, Yang Liu, Guanbin Li
  • Under Review, 2026 [paper][code] ★
Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification
  • Tianyi Wang, Long Li, Hongcan Guo, Yibiao Chen, Yixia Li, Yong Wang, Yun Chen, Guanhua Chen
  • ICML, 2026 [CCF-A][paper][code]
From Word to World: Can Large Language Models be Implicit Text-based World Models?
  • Yixia Li, Hongru Wang, Jiahao Qiu, Zhenfei Yin, Dongdong Zhang, Cheng Qian, Zeping Li, Pony Ma, Guanhua Chen, Heng Ji
  • ACL Main, 2026 [Oral, Top4%][CCF-A][paper][code] ★ 🤗
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation
  • Yixia Li*, Yaqing Shi*, Zhiwen Ruan, Dongdong Zhang, Lingjie Jiang, Shaohan Huang, Yun Chen, Guanhua Chen, Furu Wei
  • ACL Main, 2026 [Oral, Top4%][CCF-A][paper][code]
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
  • Tianyi Wang*, Yixia Li*, Long Li, Yibiao Chen, Shaohan Huang, Yun Chen, Peng Li, Yang Liu, Guanhua Chen
  • ACL Main, 2026 [Oral, Top4%][CCF-A][paper][code] ★ #3 Paper of the Day
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning Systems
  • Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu
  • ACL Main, 2026 [CCF-A][paper]
Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents
  • Zeping Li, Hongru Wang, Zhao Yiwen, Guanhua Chen, Yixia Li, Keyang Chen, Yixin Cao, Guangnan Ye, Hongfeng Chai, Mengdi Wang, Zhenfei Yin
  • ACL Main, 2026 [CCF-A][paper]
From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics Models
  • Bowen Cao, Dongdong Zhang, Yixia Li, Junpeng Liu, Shijue Huang, Chufan Shi, Hongyuan Lu, Yaokang Wu, Guanhua Chen, Wai Lam, Furu Wei
  • ICLR, 2026 [CCF-A][paper]
VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
  • Lingjie Jiang, Shaohan Huang, Xun Wu, Yixia Li, Dongdong Zhang, Furu Wei
  • ICLR, 2026 [CCF-A][paper][code]
Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
  • Zhiwen Ruan, Yixia Li, He Zhu, Yun Chen, Peng Li, Yang Liu, Guanhua Chen
  • Under Review, 2026 [paper]
Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems
  • Wanxing Wu*, He Zhu*, Yixia Li*, Lei Yang, Zhao Jiehui, Hongru Wang, Jian Yang, Benyou Wang, Bingyi Jing, Guanhua Chen
  • Under Review, 2026 [paper][code]
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models Systems
  • Rui Wang, Hongru Wang, Boyang Xue, Yixia Li, Jianhui Pang, Shudong Liu, Yi Chen, Jiahao Qiu, Derek Fai Wong, Guanhua Chen, Heng Ji, Kam-Fai Wong
  • Under Review, 2026 [paper][code]
PatchWorld: Gradient-Free Optimization of Executable World Models
  • Jiaxin Bai, Yue Guo, Yifei Dong, Jiaxuan Xiong, Tianshi Zheng, Yixia Li, Tianqing Fang, Yufei Li, Yisen Gao, Haoyu Huang, Zhongwei Xie, Hong Ting Tsang, Zihao Wang, Lihui Liu, Jeff Pan, Yangqiu Song
  • Under Review, 2026 [paper][code]

2025

G2: Guided Generation for Enhanced Output Diversity in LLMs
  • Zhiwen Ruan, Yixia Li, Yefeng Liu, Yun Chen, Weihua Luo, Peng Li, Yang Liu, Guanhua Chen
  • EMNLP Main, 2025 [CCF-B, THU-A][paper][code]
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs
  • Yan Yang*, Yixia Li*, Hongru Wang, Xuetao Wei, James Jianqiao Yu, Yun Chen, Guanhua Chen
  • ACL Main, 2025 [CCF-A][paper][code]
FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only
  • He Zhu, Yifan Ding, Yicheng Tao, Zhiwen Ruan, Yixia Li, Wenjia Zhang, Yun Chen, Guanhua Chen
  • ACL Findings, 2025 [paper][code]
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
  • Hanqing Wang, Yixia Li, Shuo Wang, Guanhua Chen, Yun Chen
  • NAACL Main, 2025 [CCF-B][paper][code] 152
LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy
  • Zhiwen Ruan*, Yixia Li*, He Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang, Yun Chen, Guanhua Chen
  • NAACL Findings, 2025 [paper][code]

2024

SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
  • Yixia Li*, Boya Xiong*, Guanhua Chen, Yun Chen
  • NeurIPS, 2024 [CCF-A][paper][code]
UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization
  • Yixia Li, Rong Xiang, Yanlin Song, Jing Li
  • IEEE TNNLS, 2024 [CCF-B][paper][code]
PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning
  • Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen
  • ACL Findings, 2024 [paper][code]
Cantonese Natural Language Processing in the Transformers Era, Survey and Challenges
  • Rong Xiang, Emmanuele Chersoni, Yixia Li, Jing Li, Chu-Ren Huang
  • Journal of Language Resources and Evaluation, 2024 [paper]
[Paper Title]
  • [Author 1], [Your Name], [Other Authors]
  • [Conference/Journal, Year] [paper][code]

Academic Services

Reviewer for:

Teaching Assistant for:

Invited Talks:

Host for:

Awards and Honors