SOURCE-LINKED INTELLIGENCE

Beyond Solver Verdicts: Generative Reward Models for Autoformalization

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal translation maintains strict reference-equivalence to a designated formalization. We formalize this vulnerability as Verdict-Preserving-Unfaithfulness (VPU): a failure mode where an incorrect encoding executes successfully and matches the expected verdict. We theoretically prove that structural, verdict-only verification heuristics are mathematically bounded to chance-level detection on these deceptively valid traces. To resolve this, we introduce Gener

Read original source ↗ Open in workspace

recordType

paper

region

Global