Rujun Han

I work on LLM Agents and post-training at Google. My recent work on Deep Research is now available on Gemini Enterprise and Gemini DR Max with millions of users. Previously, I spent two years at AWS AI Labs leading research in RAG, LLM evaluations, and alignment while building enterprise AI assistant services Kendra and Amazon Q.

I earned my CS Ph.D. from USC, advised by Nanyun Peng and Aram Galstyan. My thesis proposes event-centric reasoning with a wide range of AI applications. Prior to USC, I worked as a statistical researcher and data scientist, and obtained an M.Sc. in Data Science from NYU where I worked with Kyunghyun Cho.

Timeline

2024 – present

Senior Research Scientist

Google — Cloud AI Research

Working on LLM Agents, post-training, and distillation. Led work on Deep Research, now serving millions of users on Gemini.

2022 – 2024

Applied Scientist

Amazon Web Services — AI Labs

Led research on open-domain search and QA. Built enterprise AI assistant services including Kendra and Amazon Q.

2017 – 2018

Senior Associate, Data Scientist

Commonwealth Bank

Built the bank's first ML model and big data pipeline for commercial lending risk assessment.

2015 – 2017

Senior Research Analyst

Federal Reserve Bank of New York

Applied statistical models (hidden factor models, time-series analysis) to predict economic and financial indicators. Contributed to Nowcast, UIG, and Monetary Policy research.

2018 – 2022

Ph.D. in Computer Science

University of Southern California

2015 – 2018

M.Sc. in Data Science

New York University

2010 – 2014

B.A. in Economics and Mathematics

Hamilton College

Publications

Agent: Deep Research, Memory, Context Management

Deep Researcher with Test-Time Diffusion

Rujun Han*, Yanfei Chen*, Zoey CuiZhu, Lesly Miculicich, Guan Sun, Yuanjun Bi, Weiming Wen, Hui Wan, Chunfeng Wen, Solène Maître, George Lee, Vishy Tirumalashetty, Emily Xue, Zizhao Zhang, Salem Haykal, Burak Gokturk, Tomas Pfister, Chen-Yu Lee

SAGE: Steerable Agentic Data Generation for Deep Search Agents with Execution Feedback

Fangyuan Xu, Rujun Han, Yanfei Chen, Zifeng Wang, I-Hung Hsu, Jun Yan, Vishy Tirumalashetty, Eunsol Choi, Tomas Pfister, Chen-Yu Lee

EACL'26 Findings

SkillOS: Learning Skill Curation for Self-Evolving Agents

Siru Ouyang, Jun Yan, Yanfei Chen, Rujun Han, Zifeng Wang, Bhavana Dalvi Mishra, Rui Meng, Chun-Liang Li, Yizhu Jiao, Kaiwen Zha, Maohao Shen, Vishy Tirumalashetty, George Lee, Jiawei Han, Tomas Pfister, Chen-Yu Lee

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Siru Ouyang, Jun Yan, I-Hung Hsu, Yanfei Chen, Ke Jiang, Zifeng Wang, Rujun Han, Long T. Le, Samira Daruki, Xiangru Tang, Vishy Tirumalashetty, George Lee, Mahsan Rofouei, Hangfei Lin, Jiawei Han, Chen-Yu Lee, Tomas Pfister

ICLR'26

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context

Guangya Wan, Mingyang Ling, Xiaoqi Ren, Rujun Han, Sheng Li, Zizhao Zhang

ACL'26

Budget-Aware Tool-Use Enables Effective Agent Scaling

Tengxiao Liu, Zifeng Wang, Jin Miao, I-Hung Hsu, Jun Yan, Jiefeng Chen, Rujun Han, Fangyuan Xu, Yanfei Chen, Ke Jiang, Samira Daruki, Yi Liang, William Yang Wang, Tomas Pfister, Chen-Yu Lee

COLM'26

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialog Agents

Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le, Yiwen Song, Yanfei Chen, Hamid Palangi, Tianlong Chen, Huan Liu, Chen-Yu Lee, Tomas Pfister

ACL'25

Post-training: RL, Distillation

Supervised Reinforcement Learning: From Expert Trajectories to Step-Wise Reasoning

Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han, Gufeng Zhang, Yanfei Chen, Wei Wang, Tomas Pfister, Chen-Yu Lee

ICLR'26

Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling

Wenda Xu, Rujun Han, Zifeng Wang, Long T. Le, Dhruv Madeka, Lei Li, William Yang Wang, Rishabh Agarwal, Chen-Yu Lee, Tomas Pfister

ICLR'25

Reverse Thinking Makes LLMs Stronger Reasoners

Justin Chih-Yao Chen, Zifeng Wang, Hamid Palangi, Rujun Han, Sayna Ebrahimi, Long Le, Vincent Perot, Swaroop Mishra, Mohit Bansal, Chen-Yu Lee, Tomas Pfister

NAACL'25

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang, Jun Yan, Rujun Han, Yanfei Chen, Vishy Tirumalashetty, George Lee, Tomas Pfister, Chen-Yu Lee

RAG

CiteEval: Principle-Driven Citation Evaluation for Source Attribution

Yumo Xu, Peng Qi, Jifan Chen, Kunlun Liu, Rujun Han, Lan Liu, Bonan Min, Vittorio Castelli, Arshit Gupta, Zhiguo Wang

ACL'25

RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering

Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli

EMNLP'24

Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models

Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang

EMNLP'24

RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering

Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth

ACL'23 Findings

Other Prior Work

Towards Compute-Optimal Many-Shot In-Context Learning

Shahriar Golchin, Yanfei Chen, Rujun Han, Manan Gandhi, Tianli Yu, Swaroop Mishra, Mihai Surdeanu, Rishabh Agarwal, Chen-Yu Lee, Tomas Pfister

COLM'25

ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems

Sarik Ghazarian*, Yijia Shao*, Rujun Han, Aram Galstyan, Nanyun Peng

ACL'23

Event-centric Reasoning with Neuro-Symbolic Networks and Knowledge Incorporation

Rujun Han

Ph.D. Thesis

Character-centric Story Visualization via Visual Planning and Token Alignment

Hong Chen, Rujun Han, Te-Lin Wu, Hideki Nakayama, Nanyun Peng

EMNLP'22

Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts

Rujun Han, Hong Chen, Yufei Tian, Nanyun Peng

NAACL'22

ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning

Rujun Han, I-Hung Hsu, Jiao Sun, Julia Baylon, Qiang Ning, Dan Roth, Nanyun Peng

EMNLP'21

ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning

Rujun Han, Xiang Ren, Nanyun Peng

EMNLP'21

EventPlus: A Temporal Event Understanding Pipeline

Mingyu Derek Ma, Jiao Sun, Mu Yang, Kung-Hsiang Huang, Nuan Wen, Shikhar Singh, Rujun Han, Nanyun Peng

NAACL'21 Demo

Modeling Context in Answer Sentence Selection Systems on a Latency Budget

Rujun Han, Luca Soldaini, Alessandro Moschitti

EACL'21

Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference

Yichao Zhou, Yu Yan, Rujun Han, J. Harry Caufield, Kai-Wei Chang, Yizhou Sun, Peipei Ping, Wei Wang

AAAI'21

Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction

Rujun Han, Yichao Zhou, Nanyun Peng

EMNLP'20

TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions

Qiang Ning, Hao Wu, Rujun Han, Nanyun Peng, Matt Gardner, Dan Roth

EMNLP'20

Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction

Rujun Han, Qiang Ning, Nanyun Peng

EMNLP'19

Deep Structured Neural Network for Event Temporal Relation Extraction

Rujun Han, I-Hung Hsu, Mu Yang, Aram Galstyan, Ralph Weischedel, Nanyun Peng

CoNLL'19

Conditional Word Embedding and Hypothesis Testing via Bayes-by-Backprop

Rujun Han, Michael Gill, Arthur Spirling, Kyunghyun Cho

EMNLP'18