Back to Research
Independent research

Counterexample-Guided Verifiable Reasoning — LLM + SMT solver in the loop

An LLM proposes, Z3 disposes: conflict-directed search over SMT counterexamples, evaluated against compute-matched retry baselines.

Target model Qwen3-30B-A3B (MoE, ~3B active parameters) on an A100 80 GB. The interesting comparison is like-for-like compute: generic retry vs. solver-grounded counterexamples.

Results

Every value links to the committed artifact that produces it.

MetricValueEvidence
Evaluation runs (500 problems × 3 seeds × 5 arms)7,500data/linear/problems.jsonl + scripts/run_all.sh
Ablation arms compared, one-shot → conflict-directed5scripts/run_all.sh

Running it

A Z3-only verifier demo (no live LLM generation, so no unbounded per-click cost) is planned; the repo already carries the full evaluation harness.

Stack

  • LLM
  • Z3 / SMT
  • Verification
  • Qwen3-30B-A3B
  • A100 80GB