DAPLab is a group of Columbia faculty and their PhD students at the forefront of applied research on Data, Agents and Processes (DAP). Agents have the potential to transform how humans, companies, and economies function, yet also introduce systemic risks at every level of technology and society.

The goal of the DAPLab is to pursue research to make agent-based automation accountable, reliable, and efficient, and thus trusted within organizations.

The lab pursues this vision by combining expertise across systems (OS, data, cloud), AI (ML, RL, NLP, computer vision, robotics), human-computer interaction, and operations research.

For more information about the lab, please contact ewu@cs.columbia.edu

Education and Outreach

Workshop 2025: “AI Agents for Work” On March 12, 2025, DAPLab ran the first annual workshop at the Columbia Business School. The one-day workshop to brought together over 200 industry leaders, Columbia faculty and students, and technologists who are interested in the concept of AI agents.

Speakers and panelists come from enterprises that are deploying agentic solutions, technologists and infrastructure leaders, and researchers at leading AI labs as well as Columbia. These include Jason Wei from OpenAI who led their chain-of-thought and agentic work, Danielle Perszyk from Amazon AGI, Jonathan Frankle from Databricks, Deepak Dastrala from Intellect, Cong Yu who leads AI at Celonis, and more.

Spring 2025 class: Agentic System Made Real LLMs have opened new possibilities of automated agents that plan and complete tasks on the user’s behalf. Such agents have the potential to usher in a new industrial revolution by automating organizational processes. This graduate-level course will cut across the technology stack to examine the research questions that need to be answered for agents to be possible in real tasks that matter. Each session will review 1-3 papers or systems, and discuss research opportunities that arise from the gap between existing research and enterprise requirements. Topics will span systems (data systems and ML systems), AI (LLMs, agent-based planning), HCI, and theory (reinforcement learning, markets).

Recent Publications

ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
Xiao Yu, Baolin Peng, Vineeth Vajipey, Hao Cheng, Michel Galley, Jianfeng Gao, Zhou Yu (DAPLab)
ICLR 2025

DynEx: Agentic Assistance to Bridge Design and Code
Jenny Ma, Karthik Sreedhar, Vivian Liu, Pedro Alejandro Perez, Sitong Wang, Riya Sahni, Lydia B. Chilton (DAPLab)
CHI 2025

AnimationAgents: A Multi-Modal Team of Agents for Generating, Debugging, and Human Editing of Animation Code
Vivian Liu, Rubaiat Habib Kazi, Li-Yi Wei, Matthew Fisher, Timothy Langlois, Seth Walker, Lydia B. Chilton (DAPLab)
CHI 2025

Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs
Karthik Sreedhar, Alice Cai, Jenny Ma, Jeffrey V. Nickerson, Lydia B. Chilton (DAPLab)
IUI 2025

ACE: A LLM Agent-based Negotiation Coaching System
Ryan Shea, Aymen Kallala, Xin Lucy Liu, Michael W. Morris, Zhou Yu (DAPLab)
EMNLP 2024

Members

Faculty Members

David Blei, CS, ML and Causal Inference. World leader in probabilistic ML. 10-year test of time awards at top ML conferences, including NeurIPS and ICML. Numerous awards including the AAAI John McCarthy award, Allen Newell Award, ACM Prize in Computing, Guggenheim Fellow, and Sloan Fellowship.

Richard Zemel, CS, ML. NVIDIA Pioneer of AI Award, ICML 10-year test of time award, Canadian AI Lifetime Achievement Award. Past chair of NeurIPS, FAccT conferences. Co-Founder & Research Director Vector Institute for AI, Director NSF AI Institute for ARtificial and Natural Intelligence

Carl Vondrick, CS, Computer vision. PAMI Young Researcher Awardee, NSF CAREER. Senior program chair for ICLR 2025, the top ML and AI conference along with NeurIPS and ICML.

Yunzhu Li, CS, Robotics and agents. World leader in developing embodied AI agents for real-world robotics. Best Papers at ICRA, CoRL. Sony Faculty Innovation Award.

Shipra Agrawal, IEOR, Reinforcement learning. Proved first optimality bounds of Thompson’s sampling (core algorithm in RL). NSF CAREER. Co-chair of AIStats 2025, one of the top theoretical AI conferences.

Daniel Hsu, CS, Machine Learning Theory. World leader in theoretical foundations of machine learning and AI. Sloan fellow and AI’s 10 to Watch in 2015. Co-chair of ICML 2025, the top ML conference.

Adam Elmachtoub, IEOR, Pricing, and Market Design. Built foundations of fundamental algorithms in pricing and decision-focused learning. NSF CAREER, IBM faculty award, Forbes 30 under 30, INFORMS Early Career Gaver Award.

Baishakhi Ray, CS, Software Engineering, Neurosymbolic learning. Pioneer of CodeLLMs and AI for Software Engineering. NSF CAREER, VMWare, and IBM faculty awards, IEEE CS TCSE Rising Star Award.

Junfeng Yang, CS, Systems, Security. World leader in robustness and security of AI. Winner of the Sloan fellow, Air Force YIP awardee, NSF CAREER, research awards from Google, Meta, Amazon, best paper awards at top systems and ML conferences.

Lydia Chilton, CS, Human-Centered AI. Pioneered accurate simulations of human-AI agent strategic behavior. Winner of Facebook, Adobe, and Amazon awards.

Zhou Yu, CS, NLP. Winner of the Amazon Alexa Prize, developed the best-rated chatbot system on Amazon Alexa, reaching tens of millions of customers. Forbes 30 under 30.

Kostis Kaffes, CS, Systems. Pioneered microsecond-scale decision making in cloud computing. Meta Research Award, former Google Visiting Faculty.

Eugene Wu, CS, Data management. Developed the only database system that can track row-level data-flows at near zero cost, and forms the basis of compliance-first data systems. Winner of the NSF CAREER, VLDB 2018 Test-of-time, Google, Adobe, Amazon awards.

Advisory Board

Richard Zemel, CS, AI. Director NSF AI Institute for Artificial and Natural Intelligence.

Michael Franklin, CS, UChicago. Founder of Berkeley’s AMPLab.