UCSD Hao AI Lab launches vstack and veriserve for verifiable LLM infrastructure
Automated summary · Based on collected summaries; not individually verified
Prepared by HotAI
What happened
UCSD Hao AI Lab proposes vstack, a five-stage formal verification workflow for coding agents, and releases veriserve, a verifiable PD separation service engine.
Background
What is an AI agent? Compare it with a chatbot through a document task
This article focuses on LLM-powered AI agents: systems that choose an action for a goal, obtain external results through tools, and use those results to continue or stop. An agent organizing meeting records might search files, discover that a date is missing, and inspect another record. A basic Q&A interaction generates a response; an agent also dynamically directs execution. One tool call alone does not demonstrate that control. Check the tool records and final result.
What is a workflow? Traceable tasks built from steps and conditions
A workflow organizes steps, conditions and dependencies using people, code or models. It need not use AI or eliminate judgment. Workflows typically define control more explicitly than dynamic agents, and both can combine. Validate the whole task and failures, not one successful step.
Reading notes
The event summary comes from collected excerpts. Background passages quote existing HotAI articles to explain terms and do not establish new facts about this event. Check the original sources for product results, conditions and subsequent updates.
Original source
Sources and collection timeline
| Source | Report title | Original publication time | Collected by HotAI |
|---|---|---|---|
| x.com | UCSD Hao AI Lab launches vstack and veriserve for verifiable LLM infrastructure | 2026-11-12 03:14 | 2026-11-12 03:37 |