{"slug": "autoverifier-residual-guided-non-parametric-optimization-for-reference-based", "title": "AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification", "summary": "Researchers propose AutoVerifier, a residual-guided non-parametric optimization method that learns verifier inductive biases from recurring errors to improve reference-based answer verification. On four verifier benchmarks, AutoVerifier outperforms state-of-the-art verifiers by a large margin, according to the arXiv paper 2608.25637v1.", "body_md": "arXiv:2608.25637v1 Announce Type: new\nAbstract: 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 $1+\\pi$ 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-parametric optimization method that learns these biases from recurring verifier errors. Specifically, AutoVerifier records these biases in rule cards and promotes them to code modules or prompt guidance only after replay validation detects no direct regressions, keeping accepted updates auditable, editable, and reusable. Experiments on four verifier benchmarks demonstrate that AutoVerifier outperforms state-of-the-art verifiers by a large margin.", "url": "https://wpnews.pro/news/autoverifier-residual-guided-non-parametric-optimization-for-reference-based", "canonical_source": "https://www.machinebrief.com/news/autoverifier-residual-guided-non-parametric-optimization-for-zovk", "published_at": "2026-08-27 04:00:00+00:00", "updated_at": "2026-08-27 05:19:32.492441+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research"], "entities": ["AutoVerifier", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/autoverifier-residual-guided-non-parametric-optimization-for-reference-based", "markdown": "https://wpnews.pro/news/autoverifier-residual-guided-non-parametric-optimization-for-reference-based.md", "text": "https://wpnews.pro/news/autoverifier-residual-guided-non-parametric-optimization-for-reference-based.txt", "jsonld": "https://wpnews.pro/news/autoverifier-residual-guided-non-parametric-optimization-for-reference-based.jsonld"}}