Publications
* denotes equal contribution. Also on Google Scholar.
2026
-
Skill Reuse as Compression in Agentic RL
EMNLP 2026 Conference on Empirical Methods in Natural Language Processing
@misc{xu2026skillreusecompressionagentic, title={Skill Reuse as Compression in Agentic RL}, author={Zhikun Xu and Yu Feng and Jacob Dineen and Taiwei Shi and Jieyu Zhao and Ben Zhou}, year={2026}, eprint={2605.31509}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2605.31509} } -
Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
arXiv 2026
@misc{yang2026selfevolvingllmmemoryextraction, title={Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks}, author={Yuqing Yang and Tengxiao Liu and Wang Bill Zhu and Taiwei Shi and Linxin Song and Robin Jia}, year={2026}, eprint={2604.11610}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2604.11610} } -
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
arXiv 2026
@misc{ding2026blindspotagentsafety, title={The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents}, author={Xuwei Ding and Skylar Zhai and Linxin Song and Jiate Li and Taiwei Shi and Nicholas Meade and Siva Reddy and Jian Kang and Jieyu Zhao}, year={2026}, eprint={2604.10577}, archivePrefix={arXiv}, primaryClass={cs.CR}, url={https://arxiv.org/abs/2604.10577} } -
Video-Based Reward Modeling for Computer-Use Agents
ECCV 2026 European Conference on Computer Vision
@inproceedings{song2026videobasedrewardmodelingcomputeruse, title={Video-Based Reward Modeling for Computer-Use Agents}, author={Linxin Song and Jieyu Zhang and Huanxin Sheng and Taiwei Shi and Gupta Rahul and Yang Liu and Ranjay Krishna and Jian Kang and Jieyu Zhao}, booktitle={European Conference on Computer Vision}, year={2026}, eprint={2603.10178}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2603.10178} } -
DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning
arXiv 2026
@misc{xu2026dprftlearninggeneratesynthetic, title={DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning}, author={Fangyuan Xu and Sihao Chen and Zinan Lin and Taiwei Shi and Sydney Graham and Pei Zhou and Mengting Wan and Alex Stein and Virginia Estellers and Charles Chen and Morris Sharp and Richard Speyer and Tadas Baltrusaitis and Jennifer Neville and Eunsol Choi and Longqi Yang}, year={2026}, eprint={2602.18633}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2602.18633} } -
Experiential Reinforcement Learning
arXiv 2026
@misc{shi2026experientialreinforcementlearning, title={Experiential Reinforcement Learning}, author={Taiwei Shi and Sihao Chen and Bowen Jiang and Linxin Song and Longqi Yang and Jieyu Zhao}, year={2026}, eprint={2602.13949}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2602.13949}, } -
One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence
arXiv 2026
@misc{jiang2026modelrolesmultiturnmultiagent, title={One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence}, author={Bowen Jiang and Taiwei Shi and Ryo Kamoi and Yuan Yuan and Camillo J. Taylor and Longqi Yang and Pei Zhou and Sihao Chen}, year={2026}, eprint={2602.03109}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2602.03109}, } -
CoAct-1: Computer-using Agents with Coding as Actions
ICLR 2026 International Conference on Learning Representations
@misc{song2025coact1, title={CoAct-1: Computer-using Agents with Coding as Actions}, author={Linxin Song and Yutong Dai and Viraj Prabhu and Jieyu Zhang and Taiwei Shi and Li Li and Junnan Li and Silvio Savarese and Zeyuan Chen and Jieyu Zhao and Ran Xu and Caiming Xiong}, year={2025}, eprint={2508.03923}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2508.03923} } -
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
TMLR 2026 Transactions on Machine Learning Research
@misc{shi2025efficientreinforcementfinetuningadaptive, title={Efficient Reinforcement Finetuning via Adaptive Curriculum Learning}, author={Taiwei Shi and Yiyang Wu and Linxin Song and Tianyi Zhou and Jieyu Zhao}, year={2025}, eprint={2504.05520}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2504.05520}, } -
Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation
ICML 2026 International Conference on Machine Learning
@misc{pan2025detectingfilteringunsafetraining, title={Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation}, author={Yijun Pan and Taiwei Shi and Jieyu Zhao and Jiaqi W. Ma}, year={2025}, eprint={2502.11411}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2502.11411}, } -
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
ACL 2026 Annual Meeting of the Association for Computational Linguistics
@misc{shi2025wildfeedbackaligningllmsinsitu, title={WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback}, author={Taiwei Shi and Zhuoer Wang and Longqi Yang and Ying-Chun Lin and Zexue He and Mengting Wan and Pei Zhou and Sujay Jauhar and Sihao Chen and Shan Xia and Hongfei Zhang and Jieyu Zhao and Xiaofeng Xu and Xia Song and Jennifer Neville}, year={2025}, eprint={2408.15549}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2408.15549}, }
2025
-
The Hallucination Tax of Reinforcement Finetuning
EMNLP Findings 2025 Findings of the Conference on Empirical Methods in Natural Language Processing
@article{song2025hallucinationtax, title={The Hallucination Tax of Reinforcement Finetuning}, author={Linxin Song and Taiwei Shi and Jieyu Zhao}, journal={arXiv preprint arXiv:2505.13988}, year={2025} } -
STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models
EMNLP 2025 Conference on Empirical Methods in Natural Language Processing
-
Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
COLM 2025 Conference on Language Modeling
@misc{song2025discoveringknowledgedeficiencieslanguage, title={Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base}, author={Linxin Song and Xuwei Ding and Jieyu Zhang and Taiwei Shi and Ryotaro Shimizu and Rahul Gupta and Yang Liu and Jian Kang and Jieyu Zhao}, year={2025}, eprint={2503.23361}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2503.23361}, } -
On the Trustworthiness of Generative Foundation Models
arXiv 2025
@misc{huang2025trustworthinessgenerativefoundationmodels, title={On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective}, author={Yue Huang and Chujie Gao and Siyuan Wu and Haoran Wang and Xiangqi Wang and Yujun Zhou and Yanbo Wang and Jiayi Ye and Jiawen Shi and Qihui Zhang and Yuan Li and Han Bao and Zhaoyi Liu and Tianrui Guan and Dongping Chen and Ruoxi Chen and Kehan Guo and Andy Zou and Bryan Hooi Kuen-Yew and Caiming Xiong and Elias Stengel-Eskin and Hongyang Zhang and Hongzhi Yin and Huan Zhang and Huaxiu Yao and Jaehong Yoon and Jieyu Zhang and Kai Shu and Kaijie Zhu and Ranjay Krishna and Swabha Swayamdipta and Taiwei Shi and Weijia Shi and Xiang Li and Yiwei Li and Yuexing Hao and Yuexing Hao and Zhihao Jia and Zhize Li and Xiuying Chen and Zhengzhong Tu and Xiyang Hu and Tianyi Zhou and Jieyu Zhao and Lichao Sun and Furong Huang and Or Cohen Sasson and Prasanna Sattigeri and Anka Reuel and Max Lamparth and Yue Zhao and Nouha Dziri and Yu Su and Huan Sun and Heng Ji and Chaowei Xiao and Mohit Bansal and Nitesh V. Chawla and Jian Pei and Jianfeng Gao and Michael Backes and Philip S. Yu and Neil Zhenqiang Gong and Pin-Yu Chen and Bo Li and Xiangliang Zhang}, year={2025}, eprint={2502.14296}, archivePrefix={arXiv}, primaryClass={cs.CY}, url={https://arxiv.org/abs/2502.14296}, }
2024
-
How Susceptible are Large Language Models to Ideological Manipulation?
EMNLP 2024 Conference on Empirical Methods in Natural Language Processing Best Paper Runner-up at ICLR 2024 Workshop on SeT LLM
-
Can Language Model Moderators Improve the Health of Online Discourse?
NAACL 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
@misc{cho2023language, title={Can Language Model Moderators Improve the Health of Online Discourse?}, author={Hyundong Cho and Shuai Liu and Taiwei Shi and Darpan Jain and Basem Rizk and Yuyang Huang and Zixun Lu and Nuan Wen and Jonathan Gratch and Emilio Ferrera and Jonathan May}, year={2023}, eprint={2311.10781}, archivePrefix={arXiv}, primaryClass={cs.CL} } -
Safer-Instruct: Aligning Language Models with Automated Preference Data
NAACL 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
2023
-
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
EMNLP 2023 Conference on Empirical Methods in Natural Language Processing
@inproceedings{li2023coannotating, title={CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation}, author={Minzhi Li and Taiwei Shi and Caleb Ziems and Min-Yen Kan and Nancy F. Chen and Zhengyuan Liu and Diyi Yang}, booktitle={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing}, year={2023}, } -
Neural Story Planning
AAAI Workshop 2023 AAAI Workshop on Creative AI Across Modalities
@inproceedings{ ye2023neural, title={Neural Story Planning}, author={Anbang Ye and Christopher Zhang Cui and Taiwei Shi and Mark Riedl}, booktitle={The AAAI-23 Workshop on Creative AI Across Modalities}, year={2023}, url={https://openreview.net/forum?id=cLBEKlu5WZK} }
No publications match your search.