Cloud and AI research
Groundbreaking research to infuse AI into Google products and infrastructure.
About us
Dedicated to conducting transformative, high-impact research and achieving fundamental breakthroughs in artificial intelligence and AI systems. We explore novel, high-potential directions, pioneering a new class of agents designed to automate and augment complex tasks.
Expert & vertical agents
We develop agents designed to automate and augment complex professional workflows. This includes pioneering agents for AI research (AI Researcher), ML engineering (ML Engineer), data science (Data Scientist), and creative content generation (Co-Director).
Foundational agent capabilities
Our research builds the core technologies that enable more powerful and scalable agents. Key areas include developing robust long-term memory (Reflective Memory Management), automating the design of effective multi-agent systems (Agent Co-Designer), and establishing verifiable agent safety guardrails (VeriGuard).
Deep reasoning and research
We focus on advancing the deep reasoning capabilities of AI agents (TTD-DR). This work aims to push the state-of-the-art for systems that can conduct complex, multi-step research and analysis, with the goal of significantly outperforming existing industry benchmarks.
“We have moved past the era of simply training larger models; the real frontier is building autonomous systems that can reason, remember, and self-evolve. Watching our research bank hit SOTA milestones is exciting, but seeing an agentic ecosystem take on expert-level tasks—like automated research, forecasting massive enterprise workflows, or optimizing data center designs from scratch—is an incredibly inspiring thing to witness from the inside.”
Featured research
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.
ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI
Jaehyun Nam, Jinsung Yoon, Yanzhou Pan, Yubo Wang, Rui Meng, Parthasarathy Ranganathan, Tomas Pfister.
AIM: Agentic Idea Management for Automated Research
Hyeong Kyu Choi, Bhavana Dalvi Mishra, Jiefeng Chen, Mihir Parmar, Rui Meng, Chun-Liang Li, Xiangru Tang, Sharon Li, Jinsung Yoon, Tomas Pfister.
-
ICML 2026
PaperBanana: Automating Academic Illustration for AI Scientists
Dawei Zhu, Rui Meng, Yale Song, Xiyu Wei, Sujian Li, Tomas Pfister, Jinsung Yoon.
-
arXiv
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
Rui Meng, Bhavana Dalvi Mishra, Jiefeng Chen, Chun-Liang Li, Palash Goyal, Mihir Parmar, Yiwen Song, Yale Song, Rajarishi Sinha, Parthasarathy Ranganathan, Burak Gokturk, Jinsung Yoon, Tomas Pfister
-
ICML 2026
MARS: Modular Agent with Reflective Search for Automated AI Research
Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam, Rui Meng, Tomas Pfister, Jinsung Yoon.
-
ICML 2026
Co-Director: Agentic Generative Video Storytelling
Yale Song, Yiwen Song, Nick Losier, Nathan Hodson, Ye Jin, Rhyard Zhu, Yan Xu, Daniel Vlasic, Carina Claassen, Jasmine Leon, Khanh G. LeViet, Zack Chomyn, Joe Timmons, Brett Slatkin, Scott Penberthy, Tomas Pfister
-
ICML 2026
TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems
Md Atik Ahamed, Mihir Parmar, Palash Goyal, Yiwen Song, Long T. Le, Qiang Cheng, Chun-Liang Li, Hamid Palangi, Jinsung Yoon, Tomas Pfister.
-
ICLR 2026
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 2026
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 2026
ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning
Jihye Choi, Jinsung Yoon, Jiefeng Chen, Somesh Jha, Tomas Pfister.
-
EACL 2026
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.
-
NeurIPS 2025
MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
Jaehyun Nam, Jinsung Yoon, Jiefeng Chen, Jinwoo Shin, Sercan O Arik, Tomas Pfister.
Publications
ICLR 2026: 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 2026: 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 2026: TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
Yongchao Chen, Jiefeng Chen, Rui Meng, Ji Yin, Na Li, Chuchu Fan, Chi Wang, Tomas Pfister, Jinsung Yoon.
ICLR 2026: CoDA: Agentic Systems for Collaborative Data Visualization
Zichen Chen, Jiefeng Chen, Sercan O Arik, Misha Sra, Tomas Pfister, Jinsung Yoon.
ICLR 2026: ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning
Jihye Choi, Jinsung Yoon, Jiefeng Chen, Somesh Jha, Tomas Pfister.
TMLR 2025: SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling
Jiefeng Chen, Jie Ren, Xinyun Chen, Chengrun Yang, Ruoxi Sun, Jinsung Yoon, Sercan Ö. Arık.
NeurIPS 2025: Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
Shangbin Feng, Zifeng Wang, Palash Goyal, Yike Wang, Weijia Shi, Huang Xia, Hamid Palangi, Luke Zettlemoyer, Yulia Tsvetkov, Chen-Yu Lee, Tomas Pfister.
NeurIPS 2025: MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
Jaehyun Nam, Jinsung Yoon, Jiefeng Chen, Jinwoo Shin, Sercan O Arik, Tomas Pfister.
NeurIPS 2025: Hybrid Latent Reasoning via Reinforcement Learning
Zhenrui Yue, Bowen Jin, Huimin Zeng, Honglei Zhuang, Zhen Qin, Jinsung Yoon, Lanyu Shang, Jiawei Han, Dong Wang.
Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, Tomas Pfister, Hamid Palangi.
EMNLP 2025: PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving
Mihir Parmar, Palash Goyal, Xin Liu, Yiwen Song, Mingyang Ling, Chitta Baral, Hamid Palangi, Tomas Pfister.
EMNLP 2025: SQUARE: Unsupervised Retrieval Adaptation via Synthetic Data
Jinsung Yoon, Junhao Zeng, Sercan O Arik.
COLM 2025: 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 2025: Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan O Arik, Dong Wang, Hamed Zamani, Jiawei Han.
Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, Sercan O Arik.
ACL 2025: Embedding-Converter: A Unified Framework for Cross-Model Embedding Transformation
Jinsung Yoon, Sercan O Arik.
ACL 2025: Debiasing Online Preference Learning via Preference Feature Preservation
Dongyoung Kim, Jinsung Yoon, Jinwoo Shin, Jaehyung Kim.
ACL 2025: 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 2025: Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation
Fan Yin, Zifeng Wang, I-Hung Hsu, Jun Yan, Ke Jiang, Yanfei Chen, Jindong Gu, Long T Le, Kai-Wei Chang, Chen-Yu Lee, Hamid Palangi, Tomas Pfister.
ICML 2025: LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
Bowen Jin, Jinsung Yoon, Zhen Qin, Ziqi Wang, Wei Xiong, Yu Meng, Jiawei Han, Sercan O Arik.
ICML 2025: Retrieval Augmented Time Series Forecasting
Sungwon Han, Seungeon Lee, Meeyoung Cha, Sercan O Arik, Jinsung Yoon.
ICML 2025: Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Shangbin Feng, Zifeng Wang, Yike Wang, Sayna Ebrahimi, Hamid Palangi, Lesly Miculicich, Achin Kulshrestha, Nathalie Rauschmayr, Yejin Choi, Yulia Tsvetkov, Chen-Yu Lee, Tomas Pfister.
NAACL 2025: 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.
ICLR 2025: 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 2025: Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
Bowen Jin, Jinsung Yoon, Jiawei Han, Sercan O. Arik.
ICLR 2025: Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Zilong Wang, Zifeng Wang, Long Le, Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, Anush Mattapalli, Ankur Taly, Jingbo Shang, Chen-Yu Lee, Tomas Pfister.
ICLR 2025: Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments
Hongjin Su, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Sercan O Arik*, Tao Yu*
ICLR 2025: BRIGHT: a realistic Benchmark for ReasonInG-Heavy reTrieval
Hongjin Su, Howard Yen, Mengzhou Xia, Han-yu Wang, Haisu Liu, Niklas Muennighoff, Weijia Shi, Ruoxi Sun, Jinsung Yoon, Sercan Ö. Arik, Danqi Chen, Tao Yu.
ICLR 2025: CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL.
Mohammadreza Pourreza*, Hailong Li*, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, Sercan O Arik. (* Equal contribution).
ICLR 2025: Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training
Maximillian Chen, Ruoxi Sun, Sercan O Arik, Tomas Pfister.
Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Sercan O Arik.
ICLR 2025: Mitigating Object Hallucination via Data Augmented Contrastive Tuning
Pritam Sarkar, Sayna Ebrahimi, Ali Etemad, Ahmad Beirami, Sercan Ö. Arık, Tomas Pfister.
ICLR 2025: Omnixr: Evaluating omni-modality language models on reasoning across modalities
Lichang Chen, Hexiang Hu, Mingda Zhang, Yiwen Chen, Zifeng Wang, Yandong Li, Pranav Shyam, Tianyi Zhou, Heng Huang, Ming-Hsuan Yang, Boqing Gong.
TMLR 2025: LLM-Guided Self-Supervised Tabular Learning With Task-Specific Pre-text Tasks
Sungwon Han, Seungeon Lee, Meeyoung Cha, Sercan O Arik, Jinsung Yoon.
EMNLP 2024: Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions
Jinsung Yoon, Raj Sinha, Sercan O Arik, Tomas Pfister.
EMNLP 2024: Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval
Yanfei Chen, Jinsung Yoon, Devendra Sachan, Qingze Wang, Vincent Cohen-Addad, Mohammad Bateni, Sebastian Riedel, Chen-Yu Lee, Tomas Pfister.
NeurIPS 2024: TableRAG: Million-Token Tabular Reasoning with Large Language Models
Si-An Chen, Lesly Miculicich, Julian Martin Eisenschlos, Zifeng Wang, Zilong Wang, Yanfei Chen, Yasuhisa Fujii, Hsuan-Tien Lin, Chen-Yu Lee, Tomas Pfister.
NeurIPS 2024: UQE: A Query Engine for Unstructured Databases
Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans.
NeurIPS 2024: Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Sercan O Arik.
NeurIPS 2024: Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang*, Sercan O Arik*.
ACL 2024: Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li, Zifeng Wang, Long Le, Abhishek Kumar, James R. Glass, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, Tomas Pfister.
ACL 2024: CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation
I-Hung Hsu, Zifeng Wang, Long Le, Lesly Miculicich, Nanyun Peng, Chen-Yu Lee, Tomas Pfister.
ACL 2024: LMDX: Language Model-based Document Information Extraction and Localization
Vincent Perot, Kai Kang, Florian Luisier, Guolong Su, Xiaoyu Sun, Ramya Sree Boppana, Zilong Wang, Zifeng Wang, Jiaqi Mu, Hao Zhang, Chen-Yu Lee, Nan Hua.
ACL 2024: Search-Adaptor: Text embedding customization for information retrieval
Jinsung Yoon, Sercan O Arik, Yanfei Chen, Tomas Pfister.
NAACL 2024: CodecLM: Aligning Language Models with Tailored Synthetic Data
Zifeng Wang, Chun-Liang Li, Vincent Perot, Long Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister.
NAACL 2024:Effective Large Language Model Adaptation for Improved Grounding and Citation Generation
Xi Ye, Ruoxi Sun, Sercan Ö. Arik, Tomas Pfister.
TMLR 2024: SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL
Ruoxi Sun, Sercan O. Arik, Hootan Nakhost, Hanjun Dai, Rajarishi Sinha, Pengcheng Yin, Tomas Pfister.
ICML 2024: Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
Sungwon Han, Jinsung Yoon, Sercan O Arik, Tomas Pfister.
ICLR 2024: Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
Zilong Wang, Hao Zhang, Chun-Liang Li, Julian Martin Eisenschlos, Vincent Perot, Zifeng Wang, Lesly Miculicich, Yasuhisa Fujii, Jingbo Shang, Chen-Yu Lee, Tomas Pfister.
ICLR 2024: TEMPO: Prompt-based generative pre-trained transformer for time series forecasting
Defu Cao, Furong Jia, Sercan O Arik, Tomas Pfister, Yixiang Zheng, Wen Ye, Yan Liu.
ICLR 2024: Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy.
TMLR 2024: Provable membership inference privacy
Zachary Izzo, Jinsung Yoon, Sercan O Arik, James Zou.
TMLR 2024: ASPEST: Bridging the gap between active learning and selective prediction
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan Arik, Somesh Jha, Tomas Pfister.
KDD 2023: VRDU: A Benchmark for Visually-rich Document Understanding
Zilong Wang, Yichao Zhou, Wei Wei, Chen-Yu Lee, Sandeep Tata.
EMNLP 2023: Adaptation with self-evaluation to improve selective prediction in LLMs
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan O Arik, Tomas Pfister, Somesh Jha.
NeurIPS TRL 2023: IngesTables: Scalable and efficient training of LLM-enabled tabular foundation models (Spotlight)
Scott Yak, Yihe Dong, Javier Gonzalvo, Sercan Arik.
TMLR 2023: Invariant Structure Learning for Better Generalization and Causal Explainability
Yunhao Ge, Sercan O Arik, Jinsung Yoon, Ao Xu, Laurent Itti, Tomas Pfister.
npj Digital Medicine 2023: EHR-Safe: Generating high-fidelity and privacy-preserving synthetic electronic health records
Jinsung Yoon, Michel Mizrahi, Nahid Farhady Ghalaty, Thomas Jarvinen, Ashwin S. Ravi, Peter Brune, Fanyu Kong, Dave Anderson, George Lee, Arie Meir, Farhana Bandukwala, Elli Kanal, Sercan Ö. Arık, Tomas Pfister.
EMNLP 2023: SQLPrompt: In-context Text-to-SQL with minimal labeled data
Ruoxi Sun, Sercan Ö Arik, Rajarishi Sinha, Hootan Nakhost, Hanjun Dai, Pengcheng Yin, Tomas Pfister.
ACL 2023: Better Zero-Shot Reasoning with Self-Adaptive Prompting
Xingchen Wan, Ruoxi Sun, Hanjun Dai, Sercan Ö. Arik, Tomas Pfister.
Some of our people
Tomas Pfister
Head, Cloud AI Research
Andrew Pan
Senior Research Engineer
Arijit Ray
Research Scientist
Bhavana Dalvi Mishra
Staff Research Scientist
Chen-Yu Lee
Principal Scientist
Chun-Liang Li
Research Scientist
George Lee
Product Manager
Han Yu
Software Engineer
Holly Huo
Program Manager
Jaehyun Nam
Research Scientist
Jason Lee
Technical Program Manager
Jiefeng Chen
Research Scientist
Jinsung Yoon
Research Scientist
Ke Jiang
Software Engineer
Lesly Miculicich
Research Software Engineer
Linfeng Song
Research Scientist
Long Le
Research Engineer
Mihir Parmar
Research Scientist
Mike Heddes
Research Software Engineer
Palash Goyal
Senior Research Scientist
Pengfei He
Research Scientist
Rahul Duggal
Senior Software Engineer
Raj Sinha
Research Engineer
Rob Tang
Research Scientist
Rui Meng
Senior Research Scientist
Rujun Han
Research Scientist
Sarkar Snigdha Sarathi Das
Research Scientist
Violet Peng
Senior Staff Research Scientist
Yale Song
Research Scientist
Yanfei Chen
Software Engineer
Yifei Ming
Senior Research Scientist
Yiwen Song
Research Scientist
Yufan Zhuang
Research Scientist
Zifeng Wang
Research Scientist
Zoey CuiZhu
Research Engineer
Vishy Tirumalashetty
Group Product Manager
Locations
-
Mountain View
-
New York City
-
Pittsburgh
-
San Francisco
-
Seattle & Kirkland