AI News

Hao AI Lab proposes the vstack five-stage formal verification pipeline and the veriserve serving engine

UCSD Hao AI LabUpdated Nov 12 03:46

AI summary

Hao AI Lab proposes vstack, a five-stage formal verification pipeline for coding agents. It pins specifications via hashing, checks against real bugs and mutation gates, and validates model fidelity through execution traces; it then runs TLC, Z3, and TLAPS on CPU to prevent agents from weakening invariants, deleting timeout branches, or adding assumptions so that the solver reports 0 errors. The accompanying veriserve is a PD-disaggregated verifiable serving engine, whose KV page lifecycle design model comes with a TLAPS safety proof comprising 226 modules and 516,973 obligations. When running Qwen3-32B on a 4-GPU NVIDIA GB200 node, PdLedger incurs an average p50 TPOT overhead of +0.18%, with a 95% confidence interval upper bound of +0.68%.

Why read this

SelectedAI score 66

The original text presents the vstack five-stage verification pipeline and the measured overhead of veriserve, offering insight into one practical path for formal verification of coding agents.

Topics

Tags

Body

Naive coding agents often reward-hack formal verifiers: weakening the invariant, deleting the timeout branch, or adding an assumption so the solver reports 0 errors.

vstack blocks this across 5 stages by pinning specs by hash and validating model fidelity against real bugs, mutation gates, and execution traces before running TLC, Z3, and TLAPS on CPUs.

Source

UCSD Hao AI Lab