Research @Berkeley RDI
Advancing the Frontier of Agentic AI and Decentralized Intelligence
View All Research Publications
Agentic AI Foundation
Reasoning and Planning
Reinforcement Learning
Lifelong Learning and Self-Improvement
AI Safety and Security
Robustness and Adversarial Resilience
Oversight, Alignment, and Control
Interpretability and Monitoring
Privacy
Agentic AI Applications
Web Agents
Coding Agents
Deep Research Agents
Multi-Agent Systems
AI for Cybersecurity
AI Cybersecurity Capability Evaluation
Threat Detection and Intrusion Prevention
Automated Vulnerability Discovery
Cyber Deception and Active Defense
AI for Program Synthesis and Secure Code
Program Synthesis and Automated Code Generation
Secure Code Generation and Verification
AI-Driven Formal Methods (static analysis, correctness proofs)
Decentralization Technology
Zero-Knowledge Proofs
DeFi
Applied Cryptography
Metaverse and Synthetic Worlds
Privacy
Berkeley RDI
Advancing the science, technology, and education of decentralization and AI to empower a responsible digital economy.
Copyright © {{ "now" | date: "%Y" }} UC Regents; all rights reserved
