Co-founded actAVA, a workflow-to-model learning platform for healthcare, to give enterprises agentic sovereignty — the ability to build, test, and own their AI agents and models. I own the AI org and lead post-training of Cura 1T, a trillion-parameter healthcare model trained through a human-gated recursive self-improvement loop, which leads five of six healthcare evaluation panels. I also lead χ-Bench, our benchmark for long-horizon, policy-rich clinical workflows, and the model learning layer of KORA, our model-independent agent harness.
Led the post-training team at Salesforce AI Research, driving cross-functional initiatives for agentic AI and multi-agent orchestration. Shipped the xLAM family of function-calling models and the synthetic data pipelines behind APIGen, APIGen-MT, and AgentOhana, and scaled RL data to pretraining levels with Webscale-RL.
Developed Multi-Agent AI systems including CodeGenie Agent, SlackAgents, Ensemble Agents, and CRM WebAgent.
Developed post-training of Retroformer, a general critic model for agent self-reflection. For engineering products, I developed automatic root cause analysis algorithms, or SRE/AIOps agent.
Advisor:
Kun Zhang
Aug 2017 — May 2021
M.S. in Machine Learning
GPA: 4.00/4.00
Tech Stack
Programming Language:
Python,
JavaScript,
HTML,
CSS,
Bash,
SQL
Tools and Frameworks:
PyTorch,
Triton,
Spark,
Docker,
Kubernetes,
Streamlit,
FastAPI,
LaTex
Publications
Selected: Latest & Greatest
arXiv (arXiv). 2026.
@article{chen2026cura,
title={Cura 1T: Specialized Model for Agentic Healthcare},
author={Chen, Haolin and Qi, Leon and Brown, Steve and Metelski, Deon and Xia, Tao and Lee, Joonyul and Wang, Qixuan and Riley, Kevin and Wang, Frank and Yao, Weiran},
journal={arXiv preprint arXiv:2607.15314},
year={2026}
}
Haolin Chen,
Deon Metelski,
Leon Qi,
Tao Xia,
Joonyul Lee,
Steve Brown,
Kevin Riley,
Frank Wang,
T. Y. Alvin Liu,
Hank Capps,
Zeyu Tang,
Xiangchen Song,
Lingjing Kong,
Fan Feng,
Tianyi Zeng,
Zhiwei Liu,
Zixian Ma,
Hang Jiang,
Fangli Geng,
Yuan Yuan,
Chenyu You,
Qingsong Wen,
Hua Wei,
Yanjie Fu,
Yue Zhao,
Carl Yang,
Biwei Huang,
Kun Zhang,
Caiming Xiong,
Sanmi Koyejo,
Eric P. Xing,
Philip S. Yu,
Weiran Yao
arXiv (arXiv). 2026.
@article{chen2026chibench,
title={{$\chi$}-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?},
author={Chen, Haolin and Metelski, Deon and Qi, Leon and Xia, Tao and Lee, Joonyul and Brown, Steve and Riley, Kevin and Wang, Frank and Liu, T. Y. Alvin and Capps, Hank and others},
journal={arXiv preprint arXiv:2605.16679},
year={2026}
}
Zhepeng Cen,
Haolin Chen,
Shiyu Wang,
Zuxin Liu,
Zhiwei Liu,
Jielin Qiu,
Ding Zhao,
Silvio Savarese,
Caiming Xiong,
Huan Wang,
Weiran Yao
arXiv (arXiv). 2025.
@article{cen2025webscale,
title={Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels},
author={Cen, Zhepeng and Chen, Haolin and Wang, Shiyu and Liu, Zuxin and Liu, Zhiwei and Qiu, Jielin and Zhao, Ding and Savarese, Silvio and Xiong, Caiming and Wang, Huan and Yao, Weiran},
journal={arXiv preprint arXiv:2510.06499},
year={2025}
}
Akshara Prabhakar,
Zuxin Liu,
Jianguo Zhang,
Ming Zhu,
Shiyu Wang,
Zhiwei Liu,
Tulika Awalgaonkar,
Haolin Chen,
Thai Hoang,
Juan Carlos Niebles,
Shelby Heinecke,
Weiran Yao,
Huan Wang,
Silvio Savarese,
Caiming Xiong
arXiv (arXiv). 2025.
@article{prabhakar2025apigen,
title={APIGen-MT: Agentic PIpeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay},
author={Prabhakar, Akshara and Liu, Zuxin and Yao, Weiran and Zhang, Jianguo and Zhu, Ming and Wang, Shiyu and Liu, Zhiwei and Awalgaonkar, Tulika and Chen, Haolin and Hoang, Thai and others},
journal={arXiv preprint arXiv:2504.03601},
year={2025}
}
Haolin Chen,
Yihao Feng,
Zuxin Liu,
Weiran Yao,
Akshara Prabhakar,
Shelby Heinecke,
Ricky Ho,
Phil Mui,
Silvio Savarese,
Caiming Xiong,
Huan Wang
arXiv (arXiv). 2024.
@inproceedings{
anonymous2024language,
title={Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding},
author={Anonymous},
booktitle={Submitted to The Thirteenth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=4Po8d9GAfQ},
note={under review}
}
Zhiwei Liu*,
Weiran Yao*,
Jianguo Zhang,
Zuxin Liu,
Liangwei Yang,
Rithesh Murthy,
Tian Lan,
Ming Zhu,
Juntao Tan,
Shirley Kokane,
Thai Hoang,
Juan Carlos Niebles,
Shelby Heinecke,
Huan Wang,
Silvio Savarese,
Caiming Xiong
Computational Natural Language Learning (CoNLL). 2024.
@inproceedings{
anonymous2024pract,
title={{PRACT}: Optimizing Principled Reasoning and Acting of {LLM} Agent},
author={Anonymous},
booktitle={The SIGNLL Conference on Computational Natural Language Learning - ARR submissions},
year={2024},
url={https://openreview.net/forum?id=6p8FmlX4F5}
}
Jianguo Zhang*,
Tian Lan*,
Ming Zhu*,
Zuxin Liu*,
Thai Hoang*,
Shirley Kokane*,
Weiran Yao*,
Juntao Tan,
Akshara Prabhakar,
Haolin Chen,
Zhiwei Liu,
Yihao Feng,
Tulika Awalgaonkar,
Rithesh Murthy,
Eric Hu,
Zeyuan Chen,
Ran Xu,
Juan Carlos Niebles,
Shelby Heinecke,
Huan Wang,
Silvio Savarese,
Caiming Xiong
arXiv:2409.03215 (arXiv). 2024.
@misc{zhang2024xlamfamilylargeaction,
title={xLAM: A Family of Large Action Models to Empower AI Agent Systems},
author={Jianguo Zhang and Tian Lan and Ming Zhu and Zuxin Liu and Thai Hoang and Shirley Kokane and Weiran Yao and Juntao Tan and Akshara Prabhakar and Haolin Chen and Zhiwei Liu and Yihao Feng and Tulika Awalgaonkar and Rithesh Murthy and Eric Hu and Zeyuan Chen and Ran Xu and Juan Carlos Niebles and Shelby Heinecke and Huan Wang and Silvio Savarese and Caiming Xiong},
year={2024},
eprint={2409.03215},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2409.03215},
}
Kexun Zhang*,
Weiran Yao*,
Zuxin Liu,
Yihao Feng,
Zhiwei Liu,
Rithesh Murthy,
Tian Lan,
Lei Li,
Renze Lou,
Jiacheng Xu,
Bo Pang,
Yingbo Zhou,
Shelby Heinecke,
Silvio Savarese,
Huan Wang,
Caiming Xiong
ACM International Conference on Information and Knowledge Management (ICLR). Singapore, 2025.
@article{zhang2024diversity,
title={Diversity empowers intelligence: Integrating expertise of software engineering agents},
author={Zhang, Kexun and Yao, Weiran and Liu, Zuxin and Feng, Yihao and Liu, Zhiwei and Murthy, Rithesh and Lan, Tian and Li, Lei and Lou, Renze and Xu, Jiacheng and others},
journal={arXiv preprint arXiv:2408.07060},
year={2024}
}
Zuxin Liu,
Thai Hoang,
Jianguo Zhang,
Ming Zhu,
Tian Lan,
Shirley Kokane,
Juntao Tan,
Weiran Yao,
Zhiwei Liu,
Yihao Feng,
Rithesh Murthy,
Liangwei Yang,
Silvio Savarese,
Juan Carlos Niebles,
Huan Wang,
Shelby Heinecke,
Caiming Xiong
Neural Information Processing Systems (NeurIPS). Vancouver, Canada, 2024.
@article{liu2024apigen,
title={Apigen: Automated pipeline for generating verifiable and diverse function-calling datasets},
author={Liu, Zuxin and Hoang, Thai and Zhang, Jianguo and Zhu, Ming and Lan, Tian and Kokane, Shirley and Tan, Juntao and Yao, Weiran and Liu, Zhiwei and Feng, Yihao and others},
journal={arXiv preprint arXiv:2406.18518},
year={2024}
}
Weiran Yao,
Shelby Heinecke,
Juan Carlos Niebles,
Zhiwei Liu,
Yihao Feng,
Le Xue,
Rithesh Murthy,
Zeyuan Chen,
Jianguo Zhang,
Devansh Arpit,
Ran Xu,
Phil Mui,
Huan Wang,
Caiming Xiong,
Silvio Savarese
International Conference on Learning Representations (ICLR). Vienna, Austria, 2024.
Zhiwei Liu*,
Weiran Yao*,
Jianguo Zhang,
Liangwei Yang,
Zuxin Liu,
Juntao Tan,
Prafulla Kumar Choubey,
Tian Lan,
Jason Wu,
Huan Wang,
Shelby Heinecke,
Caiming Xiong,
Silvio Savarese
arXiv:2402.15538 (arXiv). 2024.
@article{liu2024agentlite,
title={AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System},
author={Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Yang, Liangwei and Liu, Zuxin and Tan, Juntao and Choubey, Prafulla K and Lan, Tian and Wu, Jason and Wang, Huan and others},
journal={arXiv preprint arXiv:2402.15538},
year={2024}
}
Zhiwei Liu,
Weiran Yao,
Jianguo Zhang,
Le Xue,
Shelby Heinecke,
Rithesh Murthy,
Yihao Feng,
Zeyuan Chen,
Juan Carlos Niebles,
Devansh Arpit,
Ran Xu,
Phil Mui,
Huan Wang,
Caiming Xiong,
Silvio Savarese
International Conference on Learning Representations (ICLR). 2024.
@article{liu2023bolaa,
title={Bolaa: Benchmarking and orchestrating llm-augmented autonomous agents},
author={Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Xue, Le and Heinecke, Shelby and Murthy, Rithesh and Feng, Yihao and Chen, Zeyuan and Niebles, Juan Carlos and Arpit, Devansh and others},
journal={arXiv preprint arXiv:2308.05960},
year={2023}
}
International Conference on Learning Representations (ICLR). Kigali, Rwanda, 2023.
@inproceedings{
chen2023plot,
title={{PLOT}: Prompt Learning with Optimal Transport for Vision-Language Models},
author={Guangyi Chen and Weiran Yao and Xiangchen Song and Xinyue Li and Yongming Rao and Kun Zhang},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=zqwryBoXYnh}
}
Devansh Arpit,
Matthew Fernandez,
Itai Feigenbaum,
Weiran Yao,
Chenghao Liu,
Wenzhuo Yang,
Paul Josel,
Shelby Heinecke,
Eric Hu,
Huan Wang,
Steven Hoi,
Caiming Xiong,
Kun Zhang,
Juan Carlos Niebles
arXiv:2301.10859 (arXiv). 2023.
@article{salesforce_causalai23,
title={Salesforce CausalAI Library: A Fast and Scalable framework for Causal Analysis of Time Series and Tabular Data},
author={Arpit, Devansh and Fernandez, Matthew, and Feigenbaum, Itai and Yao, Weiran and Liu, Chenghao and Yang, Wenzhuo and Josel, Paul and Heinecke, Shelby and Hu, Eric and Wang, Huan and Hoi, Stephen and Xiong, Caiming and Zhang, Kun and Niebles, Juan Carlos},
year={2023},
eprint={arXiv preprint arXiv:2301.10859},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
Jonathan Francis,
Bingqing Chen,
Weiran Yao,
Eric Nyberg,
Jean Og
International Conference on Machine Learning (ICML). Baltimore, Maryland USA, 2022.
@article{francis2022distribution,
title={Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving},
author={Francis, Jonathan and Chen, Bingqing and Yao, Weiran and Nyberg, Eric and Oh, Jean},
journal={arXiv preprint arXiv:2212.08729},
year={2022}
}
International Conference on Learning Representations (ICLR). 2022.
@article{yao2021learning,
title={Learning temporally causal latent processes from general temporal data},
author={Yao, Weiran and Sun, Yuewen and Ho, Alex and Sun, Changyin and Zhang, Kun},
journal={arXiv preprint arXiv:2110.05428},
year={2021}
}
Conference
C35
arXiv (arXiv). 2026.
@article{chen2026cura,
title={Cura 1T: Specialized Model for Agentic Healthcare},
author={Chen, Haolin and Qi, Leon and Brown, Steve and Metelski, Deon and Xia, Tao and Lee, Joonyul and Wang, Qixuan and Riley, Kevin and Wang, Frank and Yao, Weiran},
journal={arXiv preprint arXiv:2607.15314},
year={2026}
}
C34
Haolin Chen,
Deon Metelski,
Leon Qi,
Tao Xia,
Joonyul Lee,
Steve Brown,
Kevin Riley,
Frank Wang,
T. Y. Alvin Liu,
Hank Capps,
Zeyu Tang,
Xiangchen Song,
Lingjing Kong,
Fan Feng,
Tianyi Zeng,
Zhiwei Liu,
Zixian Ma,
Hang Jiang,
Fangli Geng,
Yuan Yuan,
Chenyu You,
Qingsong Wen,
Hua Wei,
Yanjie Fu,
Yue Zhao,
Carl Yang,
Biwei Huang,
Kun Zhang,
Caiming Xiong,
Sanmi Koyejo,
Eric P. Xing,
Philip S. Yu,
Weiran Yao
arXiv (arXiv). 2026.
@article{chen2026chibench,
title={{$\chi$}-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?},
author={Chen, Haolin and Metelski, Deon and Qi, Leon and Xia, Tao and Lee, Joonyul and Brown, Steve and Riley, Kevin and Wang, Frank and Liu, T. Y. Alvin and Capps, Hank and others},
journal={arXiv preprint arXiv:2605.16679},
year={2026}
}
C33
arXiv (arXiv). 2025.
@article{prabhakar2025enterprise,
title={Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics},
author={Prabhakar, Akshara and Ram, Roshan and Chen, Zixiang and Savarese, Silvio and Wang, Frank and Xiong, Caiming and Wang, Huan and Yao, Weiran},
journal={arXiv preprint arXiv:2510.17797},
year={2025}
}
C32
Zhepeng Cen,
Haolin Chen,
Shiyu Wang,
Zuxin Liu,
Zhiwei Liu,
Jielin Qiu,
Ding Zhao,
Silvio Savarese,
Caiming Xiong,
Huan Wang,
Weiran Yao
arXiv (arXiv). 2025.
@article{cen2025webscale,
title={Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels},
author={Cen, Zhepeng and Chen, Haolin and Wang, Shiyu and Liu, Zuxin and Liu, Zhiwei and Qiu, Jielin and Zhao, Ding and Savarese, Silvio and Xiong, Caiming and Wang, Huan and Yao, Weiran},
journal={arXiv preprint arXiv:2510.06499},
year={2025}
}
C31
Cheng Qian,
Zuxin Liu,
Akshara Prabhakar,
Jielin Qiu,
Zhiwei Liu,
Haolin Chen,
Shirley Kokane,
Heng Ji,
Weiran Yao,
Shelby Heinecke,
Silvio Savarese,
Caiming Xiong,
Huan Wang
arXiv (arXiv). 2025.
@article{qian2025userrl,
title={UserRL: Training Interactive User-Centric Agent via Reinforcement Learning},
author={Qian, Cheng and Liu, Zuxin and Prabhakar, Akshara and Qiu, Jielin and Liu, Zhiwei and Chen, Haolin and Kokane, Shirley and Ji, Heng and Yao, Weiran and Heinecke, Shelby and Savarese, Silvio and Xiong, Caiming and Wang, Huan},
journal={arXiv preprint arXiv:2509.19736},
year={2025}
}
C30
Zhiwei Liu,
Jielin Qiu,
Shiyu Wang,
Jianguo Zhang,
Zuxin Liu,
Roshan Ram,
Haolin Chen,
Weiran Yao,
Shelby Heinecke,
Silvio Savarese,
Huan Wang,
Caiming Xiong
arXiv (arXiv). 2025.
@article{liu2025mcpeval,
title={MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models},
author={Liu, Zhiwei and Qiu, Jielin and Wang, Shiyu and Zhang, Jianguo and Liu, Zuxin and Ram, Roshan and Chen, Haolin and Yao, Weiran and Heinecke, Shelby and Savarese, Silvio and Wang, Huan and Xiong, Caiming},
journal={arXiv preprint arXiv:2507.12806},
year={2025}
}
C29
Akshara Prabhakar,
Zuxin Liu,
Jianguo Zhang,
Ming Zhu,
Shiyu Wang,
Zhiwei Liu,
Tulika Awalgaonkar,
Haolin Chen,
Thai Hoang,
Juan Carlos Niebles,
Shelby Heinecke,
Weiran Yao,
Huan Wang,
Silvio Savarese,
Caiming Xiong
arXiv (arXiv). 2025.
@article{prabhakar2025apigen,
title={APIGen-MT: Agentic PIpeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay},
author={Prabhakar, Akshara and Liu, Zuxin and Yao, Weiran and Zhang, Jianguo and Zhu, Ming and Wang, Shiyu and Liu, Zhiwei and Awalgaonkar, Tulika and Chen, Haolin and Hoang, Thai and others},
journal={arXiv preprint arXiv:2504.03601},
year={2025}
}
C28
Jianguo Zhang,
Thai Hoang,
Ming Zhu,
Zuxin Liu,
Shiyu Wang,
Tulika Awalgaonkar,
Akshara Prabhakar,
Haolin Chen,
Weiran Yao,
Zhiwei Liu,
Juntao Tan,
Juan Carlos Niebles,
Shelby Heinecke,
Huan Wang,
Silvio Savarese,
Caiming Xiong
arXiv (arXiv). 2025.
@article{zhang2025actionstudio,
title={ActionStudio: A Lightweight Framework for Data and Training of Large Action Models},
author={Zhang, Jianguo and Hoang, Thai and Zhu, Ming and Liu, Zuxin and Wang, Shiyu and Awalgaonkar, Tulika and Prabhakar, Akshara and Chen, Haolin and Yao, Weiran and Liu, Zhiwei and others},
journal={arXiv e-prints},
pages={arXiv--2503},
year={2025}
}
C27
Juntao Tan,
Liangwei Yang,
Zuxin Liu,
Zhiwei Liu,
Rithesh Murthy,
Tulika Manoj Awalgaonkar,
Jianguo Zhang,
Weiran Yao,
Ming Zhu,
Shirley Kokane,
Silvio Savarese,
Huan Wang,
Caiming Xiong,
Shelby Heinecke
arXiv (arXiv). 2025.
@article{tan2025personabench,
title={PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data},
author={Tan, Juntao and Yang, Liangwei and Liu, Zuxin and Liu, Zhiwei and Murthy, Rithesh and Awalgaonkar, Tulika Manoj and Zhang, Jianguo and Yao, Weiran and Zhu, Ming and Kokane, Shirley and others},
journal={arXiv preprint arXiv:2502.20616},
year={2025}
}
C26
Shirley Kokane,
Ming Zhu,
Tulika Awalgaonkar,
Jianguo Zhang,
Thai Hoang,
Akshara Prabhakar,
Zuxin Liu,
Tian Lan,
Liangwei Yang,
Juntao Tan,
Rithesh Murthy,
Weiran Yao,
Zhiwei Liu,
Juan Carlos Niebles,
Huan Wang,
Shelby Heinecke,
Caiming Xiong,
Silvio Savarese
arXiv (arXiv). 2024.
C25
Haolin Chen,
Yihao Feng,
Zuxin Liu,
Weiran Yao,
Akshara Prabhakar,
Shelby Heinecke,
Ricky Ho,
Phil Mui,
Silvio Savarese,
Caiming Xiong,
Huan Wang
arXiv (arXiv). 2024.
@inproceedings{
anonymous2024language,
title={Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding},
author={Anonymous},
booktitle={Submitted to The Thirteenth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=4Po8d9GAfQ},
note={under review}
}
C24
Zhiwei Liu*,
Weiran Yao*,
Jianguo Zhang,
Zuxin Liu,
Liangwei Yang,
Rithesh Murthy,
Tian Lan,
Ming Zhu,
Juntao Tan,
Shirley Kokane,
Thai Hoang,
Juan Carlos Niebles,
Shelby Heinecke,
Huan Wang,
Silvio Savarese,
Caiming Xiong
Computational Natural Language Learning (CoNLL). 2024.
@inproceedings{
anonymous2024pract,
title={{PRACT}: Optimizing Principled Reasoning and Acting of {LLM} Agent},
author={Anonymous},
booktitle={The SIGNLL Conference on Computational Natural Language Learning - ARR submissions},
year={2024},
url={https://openreview.net/forum?id=6p8FmlX4F5}
}
C23
Jianguo Zhang*,
Tian Lan*,
Ming Zhu*,
Zuxin Liu*,
Thai Hoang*,
Shirley Kokane*,
Weiran Yao*,
Juntao Tan,
Akshara Prabhakar,
Haolin Chen,
Zhiwei Liu,
Yihao Feng,
Tulika Awalgaonkar,
Rithesh Murthy,
Eric Hu,
Zeyuan Chen,
Ran Xu,
Juan Carlos Niebles,
Shelby Heinecke,
Huan Wang,
Silvio Savarese,
Caiming Xiong
arXiv:2409.03215 (arXiv). 2024.
@misc{zhang2024xlamfamilylargeaction,
title={xLAM: A Family of Large Action Models to Empower AI Agent Systems},
author={Jianguo Zhang and Tian Lan and Ming Zhu and Zuxin Liu and Thai Hoang and Shirley Kokane and Weiran Yao and Juntao Tan and Akshara Prabhakar and Haolin Chen and Zhiwei Liu and Yihao Feng and Tulika Awalgaonkar and Rithesh Murthy and Eric Hu and Zeyuan Chen and Ran Xu and Juan Carlos Niebles and Shelby Heinecke and Huan Wang and Silvio Savarese and Caiming Xiong},
year={2024},
eprint={2409.03215},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2409.03215},
}
C22
Kexun Zhang*,
Weiran Yao*,
Zuxin Liu,
Yihao Feng,
Zhiwei Liu,
Rithesh Murthy,
Tian Lan,
Lei Li,
Renze Lou,
Jiacheng Xu,
Bo Pang,
Yingbo Zhou,
Shelby Heinecke,
Silvio Savarese,
Huan Wang,
Caiming Xiong
ACM International Conference on Information and Knowledge Management (ICLR). Singapore, 2025.
@article{zhang2024diversity,
title={Diversity empowers intelligence: Integrating expertise of software engineering agents},
author={Zhang, Kexun and Yao, Weiran and Liu, Zuxin and Feng, Yihao and Liu, Zhiwei and Murthy, Rithesh and Lan, Tian and Li, Lei and Lou, Renze and Xu, Jiacheng and others},
journal={arXiv preprint arXiv:2408.07060},
year={2024}
}
C21
Zuxin Liu,
Thai Hoang,
Jianguo Zhang,
Ming Zhu,
Tian Lan,
Shirley Kokane,
Juntao Tan,
Weiran Yao,
Zhiwei Liu,
Yihao Feng,
Rithesh Murthy,
Liangwei Yang,
Silvio Savarese,
Juan Carlos Niebles,
Huan Wang,
Shelby Heinecke,
Caiming Xiong
Neural Information Processing Systems (NeurIPS). Vancouver, Canada, 2024.
@article{liu2024apigen,
title={Apigen: Automated pipeline for generating verifiable and diverse function-calling datasets},
author={Liu, Zuxin and Hoang, Thai and Zhang, Jianguo and Zhu, Ming and Lan, Tian and Kokane, Shirley and Tan, Juntao and Yao, Weiran and Liu, Zhiwei and Feng, Yihao and others},
journal={arXiv preprint arXiv:2406.18518},
year={2024}
}
C20
Weiran Yao,
Shelby Heinecke,
Juan Carlos Niebles,
Zhiwei Liu,
Yihao Feng,
Le Xue,
Rithesh Murthy,
Zeyuan Chen,
Jianguo Zhang,
Devansh Arpit,
Ran Xu,
Phil Mui,
Huan Wang,
Caiming Xiong,
Silvio Savarese
International Conference on Learning Representations (ICLR). Vienna, Austria, 2024.
C19
Jianguo Zhang,
Tian Lan,
Ritheesh Murthy,
Zhiwei Liu,
Weiran Yao,
Juntao Tan,
Thai Hoang,
Lianwei Yang,
Yihao Feng,
Zuxin Liu,
Tulika Awalgaonkar,
Juan Carlos Niebles,
Silvio Savarese,
Shelby Heinecke,
Huan Wang,
Caiming Xiong
arXiv:2402.15506 (arXiv). 2024.
@article{zhang2024agentohana,
title={AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning},
author={Zhang, Jianguo and Lan, Tian and Murthy, Rithesh and Liu, Zhiwei and Yao, Weiran and Tan, Juntao and Hoang, Thai and Yang, Liangwei and Feng, Yihao and Liu, Zuxin and others},
journal={arXiv preprint arXiv:2402.15506},
year={2024}
}
C18
Zhiwei Liu*,
Weiran Yao*,
Jianguo Zhang,
Liangwei Yang,
Zuxin Liu,
Juntao Tan,
Prafulla Kumar Choubey,
Tian Lan,
Jason Wu,
Huan Wang,
Shelby Heinecke,
Caiming Xiong,
Silvio Savarese
arXiv:2402.15538 (arXiv). 2024.
@article{liu2024agentlite,
title={AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System},
author={Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Yang, Liangwei and Liu, Zuxin and Tan, Juntao and Choubey, Prafulla K and Lan, Tian and Wu, Jason and Wang, Huan and others},
journal={arXiv preprint arXiv:2402.15538},
year={2024}
}
C17
arXiv:2401.07526 (arXiv). 2024.
@article{feigenbaum2024editing,
title={Editing Arbitrary Propositions in LLMs without Subject Labels},
author={Feigenbaum, Itai and Arpit, Devansh and Wang, Huan and Heinecke, Shelby and Niebles, Juan Carlos and Yao, Weiran and Xiong, Caiming and Savarese, Silvio},
journal={arXiv preprint arXiv:2401.07526},
year={2024}
}
C16
Proceedings of the Third Conference on Causal Learning and Reasoning (CLeaR). 2024.
@inproceedings{feigenbaum2024causal,
title={Causal Layering via Conditional Entropy},
author={Feigenbaum, Itai and Arpit, Devansh and Heinecke, Shelby and Niebles, Juan Carlos and Yao, Weiran and Xiong, Caiming and Savarese, Silvio and Wang, Huan},
booktitle={Proceedings of the Third Conference on Causal Learning and Reasoning},
year={2024}
}
C15
International Conference on Machine Learning (ICML). 2024.
@article{chen2024caring,
title={CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process},
author={Chen, Guangyi and Shen, Yifan and Chen, Zhenhao and Song, Xiangchen and Sun, Yuewen and Yao, Weiran and Liu, Xiao and Zhang, Kun},
journal={arXiv preprint arXiv:2401.14535},
year={2024}
}
C14
arXiv:2312.11336 (arXiv). 2023.
@article{wang2023drdt,
title={Drdt: Dynamic reflection with divergent thinking for llm-based sequential recommendation},
author={Wang, Yu and Liu, Zhiwei and Zhang, Jianguo and Yao, Weiran and Heinecke, Shelby and Yu, Philip S},
journal={arXiv preprint arXiv:2312.11336},
year={2023}
}
C13
Neural Information Processing Systems (NeurIPS). New Orleans, Louisiana, USA, 2023.
@inproceedings{NEURIPS2023_19a567ab,
author = {Song, Xiangchen and Yao, Weiran and Fan, Yewen and Dong, Xinshuai and Chen, Guangyi and Niebles, Juan Carlos and Xing, Eric and Zhang, Kun},
booktitle = {Advances in Neural Information Processing Systems},
editor = {A. Oh and T. Naumann and A. Globerson and K. Saenko and M. Hardt and S. Levine},
pages = {8092--8113},
publisher = {Curran Associates, Inc.},
title = {Temporally Disentangled Representation Learning under Unknown Nonstationarity},
url = {https://proceedings.neurips.cc/paper_files/paper/2023/file/19a567abaec3990cb40d7a013556fecd-Paper-Conference.pdf},
volume = {36},
year = {2023}
}
C12
Zhiwei Liu,
Weiran Yao,
Jianguo Zhang,
Le Xue,
Shelby Heinecke,
Rithesh Murthy,
Yihao Feng,
Zeyuan Chen,
Juan Carlos Niebles,
Devansh Arpit,
Ran Xu,
Phil Mui,
Huan Wang,
Caiming Xiong,
Silvio Savarese
International Conference on Learning Representations (ICLR). 2024.
@article{liu2023bolaa,
title={Bolaa: Benchmarking and orchestrating llm-augmented autonomous agents},
author={Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Xue, Le and Heinecke, Shelby and Murthy, Rithesh and Feng, Yihao and Chen, Zeyuan and Niebles, Juan Carlos and Arpit, Devansh and others},
journal={arXiv preprint arXiv:2308.05960},
year={2023}
}
C11
Rithesh Murthy,
Shelby Heinecke,
Juan Carlos Niebles,
Zhiwei Liu,
Le Xue,
Weiran Yao,
Yihao Feng,
Zeyuan Chen,
Akash Gokul,
Devansh Arpit,
Ran Xu,
Phil Mui,
Huan Wang,
Caiming Xiong,
Silvio Savarese
International Conference on Learning Representations (ICLR). 2024.
@article{liu2023bolaa,
title={Bolaa: Benchmarking and orchestrating llm-augmented autonomous agents},
author={Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Xue, Le and Heinecke, Shelby and Murthy, Rithesh and Feng, Yihao and Chen, Zeyuan and Niebles, Juan Carlos and Arpit, Devansh and others},
journal={arXiv preprint arXiv:2308.05960},
year={2023}
}
C10
Probabilistic Graphical Model (PGM). 2024.
@article{feigenbaum2023unlikelihood,
title={On the Unlikelihood of D-Separation},
author={Feigenbaum, Itai and Wang, Huan and Heinecke, Shelby and Niebles, Juan Carlos and Yao, Weiran and Xiong, Caiming and Arpit, Devansh},
journal={arXiv preprint arXiv:2303.05628},
year={2023}
}
C9
OpenReview (OpenReview). 2023.
@misc{
liu2023nonparametric,
title={Non-Parametric State-Space Models: Identifiability, Estimation and Forecasting},
author={Chenghao Liu and Weiran Yao and Steven Hoi and Kun Zhang},
year={2023},
url={https://openreview.net/forum?id=RVgssxlEVfl}
}
C8
International Conference on Learning Representations (ICLR). Kigali, Rwanda, 2023.
@inproceedings{
chen2023plot,
title={{PLOT}: Prompt Learning with Optimal Transport for Vision-Language Models},
author={Guangyi Chen and Weiran Yao and Xiangchen Song and Xinyue Li and Yongming Rao and Kun Zhang},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=zqwryBoXYnh}
}
C7
Devansh Arpit,
Matthew Fernandez,
Itai Feigenbaum,
Weiran Yao,
Chenghao Liu,
Wenzhuo Yang,
Paul Josel,
Shelby Heinecke,
Eric Hu,
Huan Wang,
Steven Hoi,
Caiming Xiong,
Kun Zhang,
Juan Carlos Niebles
arXiv:2301.10859 (arXiv). 2023.
@article{salesforce_causalai23,
title={Salesforce CausalAI Library: A Fast and Scalable framework for Causal Analysis of Time Series and Tabular Data},
author={Arpit, Devansh and Fernandez, Matthew, and Feigenbaum, Itai and Yao, Weiran and Liu, Chenghao and Yang, Wenzhuo and Josel, Paul and Heinecke, Shelby and Hu, Eric and Wang, Huan and Hoi, Stephen and Xiong, Caiming and Zhang, Kun and Niebles, Juan Carlos},
year={2023},
eprint={arXiv preprint arXiv:2301.10859},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
C6
Neural Information Processing Systems (NeurIPS). New Orleans, Louisiana, USA, 2022.
@article{yao2022temporally,
title={Temporally disentangled representation learning},
author={Yao, Weiran and Chen, Guangyi and Zhang, Kun},
journal={Advances in Neural Information Processing Systems},
volume={35},
pages={26492--26503},
year={2022}
}
C5
Jonathan Francis,
Bingqing Chen,
Weiran Yao,
Eric Nyberg,
Jean Og
International Conference on Machine Learning (ICML). Baltimore, Maryland USA, 2022.
@article{francis2022distribution,
title={Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving},
author={Francis, Jonathan and Chen, Bingqing and Yao, Weiran and Nyberg, Eric and Oh, Jean},
journal={arXiv preprint arXiv:2212.08729},
year={2022}
}
C4
International Conference on Machine Learning (ICML). Baltimore, Maryland USA, 2022.
@article{liu2023bolaa,
title={Bolaa: Benchmarking and orchestrating llm-augmented autonomous agents},
author={Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Xue, Le and Heinecke, Shelby and Murthy, Rithesh and Feng, Yihao and Chen, Zeyuan and Niebles, Juan Carlos and Arpit, Devansh and others},
journal={arXiv preprint arXiv:2308.05960},
year={2023}
}
C3
International Conference on Learning Representations (ICLR). 2022.
@article{yao2021learning,
title={Learning temporally causal latent processes from general temporal data},
author={Yao, Weiran and Sun, Yuewen and Ho, Alex and Sun, Changyin and Zhang, Kun},
journal={arXiv preprint arXiv:2110.05428},
year={2021}
}
C2
Bingqing Chen,
Weiran Yao,
Jonathan Francis,
Mario Berges
IEEE International Conference on Smart Grid Communications (SmartGridComm). 2020.
@INPROCEEDINGS{9302954,
author={Chen, Bingqing and Yao, Weiran and Francis, Jonathan and Bergés, Mario},
booktitle={2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)},
title={Learning a Distributed Control Scheme for Demand Flexibility in Thermostatically Controlled Loads},
year={2020},
volume={},
number={},
pages={1-7},
keywords={Buildings;Aggregates;Predictive models;Statistics;Sociology;Decentralized control;Load modeling;demand flexibility;thermostatically controlled loads;reinforcement learning;evolutionary strategies},
doi={10.1109/SmartGridComm47815.2020.9302954}
}
C1
International Conference on Prognostics and Health Management (PHM). 2018.
@inproceedings{xu2018condition,
title={Condition monitoring of wheel wear for high-speed trains: A data-driven approach},
author={Xu, Peiwen and Yao, Weiran and Zhao, Yang and Yi, Cai and Li, Lishuai and Lin, Jianhui and Tsui, Kwok Leung},
booktitle={2018 IEEE International Conference on Prognostics and Health Management (ICPHM)},
pages={1--8},
year={2018},
organization={IEEE}
}
Journal
J5
Journal of Power Sources (Journal of Power Sources). 2022.
@article{jia2022precise,
title={Precise and fast safety risk classification of lithium-ion batteries based on machine learning methodology},
author={Jia, Yikai and Li, Jiani and Yao, Weiran and Li, Yangxing and Xu, Jun},
journal={Journal of Power Sources},
volume={548},
pages={232064},
year={2022},
publisher={Elsevier}
}
J4
Transport Policy (Transport Policy). 2022.
@article{jia2022precise,
title={Precise and fast safety risk classification of lithium-ion batteries based on machine learning methodology},
author={Jia, Yikai and Li, Jiani and Yao, Weiran and Li, Yangxing and Xu, Jun},
journal={Journal of Power Sources},
volume={548},
pages={232064},
year={2022},
publisher={Elsevier}
}
J3
Advanced Energy Materials (Advanced Energy Materials). 2021.
@article{jia2021data,
title={Data-driven safety risk prediction of lithium-ion battery},
author={Jia, Yikai and Li, Jiani and Yuan, Chunhao and Gao, Xiang and Yao, Weiran and Lee, Minwoo and Xu, Jun},
journal={Advanced Energy Materials},
volume={11},
number={18},
pages={2003868},
year={2021},
publisher={Wiley Online Library}
}
J2
Transportation Research Part C: Emerging Technologies (TRC). 2021.
J1
Transportation Research Record: Journal of the Transportation Research Board (TRR). 2020.
@article{yao2020learning,
title={Learning to recommend signal plans under incidents with real-time traffic prediction},
author={Yao, Weiran and Qian, Sean},
journal={Transportation Research Record},
volume={2674},
number={6},
pages={45--59},
year={2020},
publisher={SAGE Publications Sage CA: Los Angeles, CA}
}
Engineering Projects
2025 – Present
Build, test, and own AI agents and models for the operational long tail of healthcare — KORA agent harness, CHRYSO governance suite, χ-Bench, and the Cura 1T frontier model
Jan 2024 – Present
Scalable Collaboration for Multiple AI Agents in Workspaces
Aug 2024 – Present
Enhancing IDE Productivity through AI Code Planning, Editing, and Execution
Jan 2023 – Dec 2023
AIOps Augments SREs' Capabilities for Automating Operations
Talks
Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
Sep. 2024
CAMEL-AI Workshop, Cupertino
PRAct: Optimizing Principled Reasoning and Acting of LLM Agent
Jun. 2024
Databricks Data + AI Summit, San Francisco
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
Sep. 2023
Moveworks Workshop, Mountain View
Large Actions Models in a Multi-Agent World
Sep. 2024
Dreamforce Breakout Session, San Francisco
Press
Jul. 2026
Jul. 2026
May 2026
Apr. 2026
Oct. 2024
Sep. 2024
Aug. 2024
Aug. 2024
Jul. 2024
Jul. 2024
Mar. 2024
Mar. 2024
Aug. 2023
Aug. 2023
May 2021
Mentoring
Summer 2024
Ph.D. in Computer Science, Carnegie Mellon University
AI Software Engineer
2022 — 2023
Ph.D. in Machine Learning, Carnegie Mellon University
Disentangled Representation Learning
2022 — 2023
M.S. in Machine learning, Carnegie Mellon University
Low-Rank Approximation
Now: Machine Learning Engineer at
Google2022 — 2023
Ph.D. in Computer Science, Carnegie Mellon University
Multi-Source Domain Adaptation
2022 — 2023
Ph.D. in Computer Science, Southeast University
Disentangled Representation Learning
