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