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

• URL: http://arxiv.org/abs/2608.25637v1
• Date: Wed, 26 Aug 2026 11:06:40 GMT
• Title: AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification
• Abstract summary: AutoVerifier learns implicit assumptions from recurring verifier errors.<n>Experiments on four verifier benchmarks demonstrate that AutoVerifier outperforms state-of-the-art verifiers by a large margin.
• Score: 5.990350746292239
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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-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.

Related papers

• FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search [88.16262636915975]
  FineVerify is a fine-grained self-verification framework for agentic search.<n>It decomposes each question into checkable sub-questions, verifies sampled candidates, and selects the candidate with the highest aggregated score.<n>FineVerify consistently outperforms standard scaling baselines.
  arXiv  Detail & Related papers  (2026-05-30T10:21:20Z)
• Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality [24.614192550852277]
  No standard measure exists for whether model-generated justifications help users distinguish correct answers from incorrect ones.<n>We formalize this idea as error verifiability and propose $v_textbal$, a balanced metric that measures whether justifications enable raters to accurately assess answer correctness.<n>We introduce two methods that succeed at improving verifiability: reflect-and-rephrase (RR) for mathematical reasoning and oracle-rephrase (OR) for factual QA.
  arXiv  Detail & Related papers  (2026-04-06T04:53:59Z)
• PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering [71.15346406323827]
  We introduce PRIME, a benchmark for evaluating verifiers on Process-Outcome Alignment verification.<n>We find that current verifiers frequently fail to detect derivation flaws.<n>We propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
  arXiv  Detail & Related papers  (2026-02-12T04:45:01Z)
• Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning [27.979418392479033]
  Large Reasoning Models (LRMs) achieve strong performance by generating long reasoning traces with reflection.<n>We find that a substantial fraction of reflective steps consist of self-verification (recheck) that repeatedly confirm intermediate results.<n>This reveals a mismatch between how often self-verification is activated and how often it is actually useful.<n>We propose a novel, experience-driven test-time framework that reduces the overused verification.
  arXiv  Detail & Related papers  (2026-02-03T12:58:23Z)
• When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers [11.937771430269201]
  We present a systematic study across 37 large language models (LLMs)<n>We compare self-verification with verification within the same family and across different families.<n>We analyze how metrics like verifier gain and false positive rate scale with model size and post-training, and characterize differences in dataset verifiability.
  arXiv  Detail & Related papers  (2025-12-02T00:51:14Z)
• Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense [36.71358559780692]
  HERO is a reinforcement learning framework that integrates verifier signals with reward-model scores in a structured way.<n> HERO consistently outperforms RM-only and verifier-only baselines, with strong gains on both verifiable and hard-to-verify tasks.
  arXiv  Detail & Related papers  (2025-10-08T17:09:41Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Latent Veracity Inference for Identifying Errors in Stepwise Reasoning [78.29317733206643]
  We introduce Veracity Search (VS), a discrete search algorithm over veracity assignments.<n>It performs otherwise intractable inference in the posterior distribution over latent veracity values.<n>It generalizes VS, enabling accurate zero-shot veracity inference in novel contexts.
  arXiv  Detail & Related papers  (2025-05-17T04:16:36Z)
• AutoPSV: Automated Process-Supervised Verifier [10.283965168399158]
  textbfAutomated textbfProcess-textbfSupervised textbfVerifier (textbftextscAutoPSV) textscAutoPSV begins by training a verification model on the correctness of final answers. We experimentally validate that the step-level confidence changes learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps.
  arXiv  Detail & Related papers  (2024-05-27T03:44:24Z)
• From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification [118.03466985807331]
  We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.<n>We introduce the feedback-based evidence retriever(FER) that optimize the evidence retrieval process by incorporating feedback from the claim verifier.
  arXiv  Detail & Related papers  (2023-10-18T02:59:38Z)
• Benchmarking Answer Verification Methods for Question Answering-Based Summarization Evaluation Metrics [74.28810048824519]
  Question answering-based summarization evaluation metrics must automatically determine whether the QA model's prediction is correct or not. We benchmark the lexical answer verification methods which have been used by current QA-based metrics as well as two more sophisticated text comparison methods.
  arXiv  Detail & Related papers  (2022-04-21T15:43:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.