SOURCE-LINKED INTELLIGENCE

Neuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic Verification

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

While tool-augmented Large Language Models have significantly improved multi-step reasoning in quantitative STEM tasks, a critical residual failure mode remains: intermediate reasoning steps that are syntactically well-formed, mathematically executable, and unit-consistent, yet contextually ungrounded. Current approaches either rely on formal verifiers that cannot assess semantic intent, or burden Process Reward Models (PRMs) with the dual task of checking both arithmetic and logic. In this paper, we propose a neuro-symbolic framework that cleanly decouples reasoning into two formal dimensions

Read original source ↗ Open in workspace

recordType

paper

region

Global