Building the Future of Agentic & AI Systems
Submit your research to CAIS 2026 — the premier venue for rigorous, reproducible work on compound AI architectures, optimization, and deployment.
DoubleTree by Hilton San Jose
2050 Gateway Place, San Jose, CA 95110
Complimentary shuttle to/from San Jose International Airport (SJC) • Discounted parking $10/day
Group Rate: $159/night + tax
Booking details coming soon
Why CAIS?
A high-signal forum for rigorous, reproducible research on agentic and AI systems—architectures that shift the Pareto frontier through principled composition of multiple system components, smart inference-time scaling strategies, and systematic verification methods for reliable deployment.
Architectural Patterns & Composition
Networks of Networks and inference-time scaling architectures. Verifier-based systems leveraging generation/verification asymmetry. RAG, multi-agent, and tool-augmented designs.
System Optimization & Efficiency
End-to-end optimization of non-differentiable pipelines. Cost-performance trade-offs, resource allocation across components, and automated architecture search for compound systems at scale.
Engineering & Operations
MLOps for compound AI. Monitoring, debugging, observability, and specifications. Security and safety in multi-component systems. Production deployment case studies.
Evaluation & Benchmarking
Metrics for compound system performance. Reproducibility frameworks and artifact standards. Comparative evaluation methodologies and real-world impact assessment.
Conference Leadership
CAIS is guided by a Steering Committee of leading researchers from Berkeley, CMU, Brown, Microsoft Research, Databricks, Two Sigma, and Mithril — scholars and practitioners who defined the compound AI systems paradigm.
Conference Program
Four days of cutting-edge research presentations, hands-on tutorials, and community building—May 26–29, 2026 in San Jose.
Research Track
Peer-reviewed papers on architectural patterns, optimization, engineering, and evaluation of agentic AI systems. Includes keynotes, plenaries, and poster sessions.
CFP Coming SoonTutorials & Workshops
Deep dives into practical methods and frameworks—DSPy, LangChain, and more tools for building compound AI systems at scale.
Workshop and tutorial calls coming soon.
Artifact-Centric Review with Reproducibility Badges
CAIS emphasizes open artifacts, transparent evaluation, and benchmarking standards. We adopt ACM's reproducibility badging taxonomy to recognize high-quality, deployable research.
Be part of the inaugural CAIS
Submission timeline and important dates available in the Call for Papers. Early submissions encouraged.