The Data, Agents, and Processes Lab (DAPLab) at Columbia University is building the foundations for a future where AI agents safely and reliably automate complex work. We bring together researchers in data systems, applied AI, operating systems, HCI, algorithms, and business to invent the infrastructure, algorithms, and design principles needed to deploy agents in the real world.
Our work spans the full stack—from systems and training frameworks to human–agent interaction, process automation, and digital twins. We build open-source tools, collaborate closely with industry partners, and prototype agentic technologies that reimagine how work gets done. Based in the heart of New York City—home to some of the world’s largest enterprises—we are uniquely positioned to explore how agent automation transforms real organizational processes. DAPLab is a home for students, researchers, and partners who want to shape the next generation of AI-native systems.
For more information about the lab, please contact ewu@cs.columbia.edu
News & Education
Fall 2025 AI Entrepreneurship Series
The DAPLab is organizing a series of events that bring together Columbia students, faculty, and industry partners to discuss the process of transitioning lessons from research and the classroom into products and value.
Fall 2025 DAPLab Research Seminar
The DAPlab’s Tuesday 12PM research seminar in CSB 453 (CS Conference Room) invites speakers that can share cutting-edge agent-systems research or can talk about processes in their organizations and how they are trying to automate them.
Fall 2025 Agentic System Made Real Course
This second iteration of the course will be led by Junfeng Yang, with a focus on security issues related to AI Agents. Check the Spring 2025 version here.
We plan to run the second iteration of our AI Agents for Work workshop in October 2025. The first day will be a public event with cutting edge research, war stories from deployments, and engaging panels. The second day will be private for DAPLab industry partners to deeply engage with the students, faculty, and other partners.
Events
-
2025-12-09
Validation Techniques for Offensive Security Agents Brendan Dolan-GavittLarge language models are increasingly helping to automate vulnerability discovery and exploit...
-
2025-12-02
AI Entrepreneurship: Obstacles, Opportunities, and Outcomes Anish Das Sarma, Reinforce LabsBuilding an AI startup today is exciting, but also uniquely challenging. In this talk, I’ll of...
-
2025-11-21
Building Foundation Models at Scale: System Experiences and Challenges Jingren ZhouThe rapid evolution of AI has led to the emergence of massive and complex foundation models th...
-
2025-11-18
AI Site Reliability Engineers: Automating Incident Response in Complex Systems Anish Agrawal, TraversalIn this presentation, I will describe ongoing work at Traversal, where our team is developing ...
Publications
-
January 2026
Please Don't Kill My Vibe: Empowering Agents with Data Flow Control -
December 2025
LLM Generated Persona is a Promise with a Catch -
December 2025
Agents for Web Testing: A Case Study in the Wild -
December 2025
Data Mixture Optimization: A Multi-Fidelity Multi-Scale Bayesian Framework -
December 2025
Tail-Optimized Caching for LLM Inference -
December 2025
Multi-Agent Markov Entanglement -
December 2025
Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper -
December 2025
Q-learning with Posterior Sampling