SOURCE-LINKED INTELLIGENCE

AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification

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

Reference-based verifiers are important for evaluating reasoning models and providing accurate outcome rewards in reinforcement learning with verifiable rewards. To improve verification accuracy, prior work has explored rule-based, model-based, and tool-augmented verifiers for checking answer equivalence across diverse answer forms. However, the equivalence of answer forms such as $1+3.14$ and $1+π$ may depend on the question and scoring criterion. We frame such implicit assumptions as verifier inductive biases. To address this challenge, we propose AutoVerifier, a residual-guided non-parametr

Read original source ↗ Open in workspace

recordType

paper

region

Global