Publications

Agents: 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 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
• 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
• In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents.
  Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long T. Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee, Tomas Pfister. ACL’25
• COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context.
  Guangya Wan, Mingyang Ling, Xiaoqi Ren, Rujun Han, Sheng Li, Zizhao Zhang
• 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.

LLM Post-training: distillation, RL

• Supervised reinforcement learning: From expert trajectories to step-wise reasoning.
  Yihe Deng, I-Hung, 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

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. [Code]
  Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli. EMNLP’24 main
• Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models. [Code]
  Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang. EMNLP’24 main
• RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering. [Code]
  Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang and 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. [Code]
  Hong Chen, Rujun Han, Te-Lin Wu, Hideki Nakayama and Nanyun Peng. EMNLP’22
• Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts [Code]
  Rujun Han, Hong Chen, Yufei Tian and Nanyun Peng. NAACL’22
• ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning. [Code]
  Rujun Han, I-Hung Hsu, Jiao Sun, Julia Baylon, Qiang Ning, Dan Roth and Nanyun Peng. EMNLP’21
• ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning. [Code]
  Rujun Han, Xiang Ren and 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 Demostrations Track
• Modeling Context in Answer Sentence Selection Systems on a Latency Budget.
  Rujun Han, Luca Soldaini and 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 and Wei Wang. AAAI’21 [acceptance rate: 21.0%]
• Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction. [Code]
  Rujun Han, Yichao Zhou and Nanyun Peng. EMNLP’20 [acceptance rate: 22.4%]
• TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions. [Code]
  Qiang Ning, Hao Wu, Rujun Han, Nanyun Peng, Matt Gardner and Dan Roth. EMNLP’20 [acceptance rate: 22.4%]
• Becoming a Dentist: Tracing Professional Identity Development Through Mixed Methods Data Mining of Student Reflections.
  Alyssa Wise, Sameen Reza and Rujun Han. ICLS’20
• Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction. [Code]
  Rujun Han, Qiang Ning and Nanyun Peng. EMNLP’19 [acceptance rate: 23.8%]
• Deep Structured Neural Network for Event Temporal Relation Extraction
  Rujun Han, I-Hung Hsu, Mu Yang, Aram Galstyan, Ralph Weischedel and Nanyun Peng. CoNLL’19 [acceptance rate: 22.7%]
• Contextualized Word Embeddings Enhanced Event Temporal Relation Extraction for Story Understanding
  Rujun Han, Mengyue Liang, Bashar Alhafni and Nanyun Peng. NAACL’19 Workshop on Narrative Understanding
• Conditional Word Embedding and Hypothesis Testing via Bayes-by-Backprop. [Code]
  Rujun Han, Michael Gill, Arthur Spirling and Kyunghyun Cho. EMNLP’18 [acceptance rate (short): 23.2%]