CAIS 2026 Program
Accepted research papers and system demonstrations
ACM CAIS 2026 will present 63 peer-reviewed research papers, 46 system demonstrations, and 6 workshops and tutorials in San Jose, May 26–29, 2026.
Accepted Papers
63 peer-reviewed research contributions on AI and Agentic systems — architectures, optimization, evaluation, engineering, and security.
Browse PapersAccepted Demos
46 working implementations of AI systems and agent systems, presented live at the conference.
Browse DemosWorkshops & Tutorials
5 workshops and a half-day tutorial on Tuesday, May 26 — agent skills, agentic software engineering, RL environments, discovery agents, healthcare AI, and more.
Browse WorkshopsCommittees
The Steering, Organizing, Program, and Artifact Evaluation Committees who shaped CAIS 2026.
Browse CommitteesBrowse the Full Schedule
All four days — workshops, paper sessions, keynotes, demos, and receptions with per-talk times and room assignments.
Keynote Speakers
Andy Konwinski
Co-founder of Databricks and Perplexity AI · Founder of Laude Institute
Laude's "Ship Your Research" mission funds open-source AI research through its Moonshots, Slingshots, and Open Frontier programs. Terminal-Bench, a Laude-backed agent benchmark, has become an industry-wide standard for measuring command line performance.
Thariq Shihipar
Member of Technical Staff, Claude Code · Anthropic
Thariq is a core builder of Claude Code, the agentic coding tool that has become one of the most widely adopted developer interfaces for working with LLMs. His technical writing on prompt caching, tool design, and "unhobbling" has shaped how practitioners think about building reliable agentic systems.
Percy Liang
Professor at Stanford · Co-founder of Together AI and Simile AI · Creator of Marin
Percy Liang is a Professor of Computer Science at Stanford University, co-founder of Together AI and Simile AI, and the creator of Marin, which aims to build frontier models fully in the open. He has made a number of contributions in AI, including the SQuAD question answering dataset, the HELM benchmarking framework, generative agents, prefix tuning, and coining the term "foundation models".
Independently Organized Events
The following events take place at external venues and are independently organized and hosted by their respective organizers. Listings are provided as a courtesy to attendees and do not constitute sponsorship, endorsement, or official affiliation with ACM CAIS.
SAO Workshop Happy Hour
Tuesday, May 26 • 6:30 PM PT • San Jose (venue TBD)
An informal reception organized by Supporting Our AI Overlords (SAO) workshop organizers. The SAO best paper award, sponsored by MongoDB, will be presented. Organized by Bauplan, Mozilla AI, and MongoDB.
RSVP on LumaSkillsBench 1.0 Launch Party
Wednesday, May 27 • Evening • San Francisco (501 2nd St)
The SkillsBench 1.0 launch, an afterparty for the Agent Skills'26 workshop featuring live demos and talks on agent benchmarking and skills design. Organized by BenchFlow, Google DeepMind, and Kernel Labs.
RSVP on Luma
