Eric Hanchen Jiang 姜汉晨

Ph.D. Student · University of California, Los Angeles

Hi! I’m Eric Jiang, a Ph.D. student in Statistics and Data Science at UCLA, advised by Prof. Kai-Wei Chang and Prof. Ying Nian Wu.

My research focuses on advancing large language models in reasoning, safety, and agentic capabilities, with the goal of building systems that are reliable, effective, and scalable for real-world applications.

I am currently developing agent harnesses for tackling challenging mathematical problems, including open problems. Looking ahead, I aim to design efficient agent infrastructure that improves how LLM-based agents use tools, memory, and long-horizon reasoning.

Photo 1 · Photo 2 · Photo 3 · Photo 4

Publications

Google Scholar

2026

Preprint

From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

Eric Hanchen Jiang, Xiao Liang, Yikai Zhang, Yingjia Wan, Mengting Li, Haikang Deng, Alexander K. Taylor, Justin Baker, Rushil Raghavan, Junyi Zhang, Ying Nian Wu, Andrea L. Bertozzi, Kai-Wei Chang, Raghu Meka, Matthew Sottile, Nanyun Peng, Amit Sahai, Terence Tao, Wei Wang

Preprint

Learning to Rank Chain-of-Thought: Using a Small Model

Eric Hanchen Jiang, Haozheng Luo, Shengyuan Pang, Xiaomin Li, Zhenting Qi, Hengli Li, Cheng-Fu Yang, Zongyu Lin, Xinfeng Li, Hao Xu, Kai-Wei Chang, Ying Nian Wu

NeurIPS Evaluations and Datasets Track

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

Wei-Chieh Huang, Weizhi Zhang, Yuchen Wu, Yankai Chen, Eric Hanchen Jiang, Wooseong Yang, Yiwei Yang, Henry Peng Zou, Hanrong Zhang, Ying Nian Wu, Haolun Wu, Kai-Wei Chang, Philip S. Yu, Xue Liu, Aylin Caliskan

NeurIPS

Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Hengli Li, Chenxi Li, Tong Wu, Xuekai Zhu, Yuxuan Wang, Zhaoxin Yu, Eric Hanchen Jiang, Song-Chun Zhu, Zixia Jia, Ying Nian Wu, Zilong Zheng

NeurIPS

Attention Sinks and Outliers in Attention Residuals

Haozheng Luo, Haoran Dai, Shaoyang Zhang, Xi Chen, Eric Hanchen Jiang, Yijiang Li, Jingyuan Huang, Chenghao Qiu, Chenwei Xu, Zhenyu Pan, Haotian Zhang, Binghui Wang, Yan Chen

NeurIPS

RECAP: Looking Once Is Not Enough for Vision-Language Reasoning

Zhaolu Kang, Tailong Luo, Chenxin Li, Zhenyu Yu, Fengyu Zhou, Jiachen Qian, Lei Wei, Shuang Chen, Jiachen Li, Yingjie He, Eric Hanchen Jiang, Rongchao Zhang, Zhengtao Yao, Hoi Leong Lee, Guansu Wang, et al.

EMNLP Main

JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction

Zhaolu Kang, Yantao Liu, Tailong Luo, Leqi Zheng, Lei Wei, Chenghua Zhu, Junhao Gong, Jiachen Qian, Eric Hanchen Jiang, Jiaxin Liu, Yuan Wang, Hao Zhang, Zixia Wang, Rong Fu, Zheng Lin, Richeng Xuan, Zhichao Hu

COLM

Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning

Eric Hanchen Jiang, L. Li, R. Sun, Xiao Liang, Y. Li, Y. Wu, Haozheng Luo, Hengli Li, Z. Zhang, Z. Kang, et al.

COLM

When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs

Edward Sun, Yuchen Wu, Zixian Ma, Eric Hanchen Jiang, Yijia Xiao, Xiaoyuan Yi, Ranjay Krishna, et al.

COLM

Decoupled Alignment for Robust Plug-and-Play Adaptation

Haozheng Luo, J. Yu, W. Zhang, J. Li, C. Qiu, Y. Wang, Eric Hanchen Jiang, J. Hu, Y. Chen, et al.

ACL Main

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy

Eric Hanchen Jiang†, Weixuan Ou†, Run Liu, Shengyuan Pang, Guancheng Wan, Ranjie Duan, Wei Dong, Kai-Wei Chang, XF Wang, Ying Nian Wu, Xinfeng Li

ACL Main

Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models

Eric Hanchen Jiang†, Guancheng Wan†, Sophia Yin†, Mengting Li†, Yuchen Wu, Xiao Liang, Xinfeng Li, Yizhou Sun, Wei Wang, Kai-Wei Chang, Ying Nian Wu

ACL Main

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability

Xiao Liang, Z.Z. Li, Zongyu Lin, Eric Hanchen Jiang, Heng Zhang, Yizhou Shen, Kai-Wei Chang, Ying Nian Wu, et al.

AAAI

DAWN: Distributed LLM Multi-Agent Workflow Synthesis

Guancheng Wan, M. Zhou, Z. Wang, X. Shang, Eric Hanchen Jiang, G. Zhang, J. Bi, Y. Ma, et al.

AAAI

Multi-head Reward Aggregation Guided by Entropy

Xinfeng Li, X. Chen, J. Fan, Eric Hanchen Jiang, M. Gao

ICLR

Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE

Guancheng Wan, L. Fu, H. Liu, Y. Jin, H.Y. Leong, Eric Hanchen Jiang, H. Geng, J. Bi, Y. Ma, et al.

2025

NeurIPS Datasets & Benchmarks

CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs

Sijia Chen, Xiaomin Li, Mengxue Zhang, Eric Hanchen Jiang, Qingcheng Zeng, Chen-Hsiang Yu

AISTATS

Statistical Guarantees for Lifelong Reinforcement Learning Using PAC-Bayesian Theory

Z. Zhang, C. Chow, Y. Zhang, Yizhou Sun, Heng Zhang, Eric Hanchen Jiang, H. Liu, F. Huang, Y. Cui, O.H.M. Padilla

2024

ICLR Tiny Papers

SDSRA: A Skill-Driven Skill-Recombination Algorithm for Efficient Policy Learning

Eric Hanchen Jiang, A. Lizarraga

Education

University of California, Los Angeles

Aug 2025 – Jun 2030 (expected)

Ph.D. in Statistics and Data Science

Advisors: Prof. Ying Nian Wu & Prof. Kai-Wei Chang

University of California, Los Angeles

Jun 2022 – Jun 2025

B.S. in Statistics & Data Science; B.S. in Mathematics of Computation

GPA: 3.85/4.00

Honors & Awards

2025UCLA Graduate Dean’s Scholar Award (GDSA)
2025Princeton University Graduate Student Fellowship (declined)
2023 – 2024Dean’s Honors List, UCLA