Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers

• URL: http://arxiv.org/abs/2509.23152v1
• Date: Sat, 27 Sep 2025 06:50:24 GMT
• Title: Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
• Authors: Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Yiwei Wang, Xiaodan Liang, Jing Tang,
• Abstract summary: Mirror-Critique is a framework that trains a verifier with informative critiques.<n>We deploy a small instruction-tuned model to synthesize high-quality critique data.<n>The resulting Mirror-Verifier is deployed to evaluate candidate solutions by generating multiple critiques per solution.
• Score: 63.99316853136304
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time scaling via solution sampling and aggregation has become a key paradigm for improving the reasoning performance of Large Language Models (LLMs). While reward model selection is commonly employed in this approach, it often fails to identify minority-yet-correct answers, which limits its effectiveness beyond that of simple majority voting. We argue that this limitation stems from a lack of informative critique signals during verifier training. To bridge this gap, we introduce Mirror-Critique, a framework that trains a verifier with informative critiques. Our key insight is to leverage the rich critique signal by contrasting model-generated solutions with ground-truth solutions. We deploy a small instruction-tuned model to synthesize high-quality critique data with rejection sampling that teaches the verifier not only what is wrong, but also why. The synthetic data is used to cold-start the LLMs in the RLVR process to further improve the verification ability. The resulting Mirror-Verifier is deployed to evaluate candidate solutions by generating multiple critiques per solution, aggregating them into a verify score used for weighted voting or selective abstention. The experimental results show that our Mirror-Verifier significantly outperforms majority voting in terms of solution accuracy and also improves the solver's honesty to recognize and abstain from answering beyond its capability boundaries.

Related papers

• LaSeR: Reinforcement Learning with Last-Token Self-Rewarding [54.72617309922891]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
  arXiv  Detail & Related papers  (2025-10-16T17:55:11Z)
• The Majority is not always right: RL training for solution aggregation [53.1050856072799]
  We train an aggregator model to review, reconcile, and synthesize a final, correct answer.<n>A key ingredient is careful balancing of easy and hard training examples.<n>We find our method, AggLM, outperforms both strong rule-based and reward-model baselines.
  arXiv  Detail & Related papers  (2025-09-08T16:39:38Z)
• TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning [11.573904453859098]
  Reinforcement Learning (RL) has become a powerful tool for enhancing the reasoning abilities of large language models (LLMs)<n>Yet, RL's success relies on the reliability of rewards, which are provided by verifiers.<n>In this paper, we expose and analyze a widespread problem--false negatives--where verifiers wrongly reject correct model outputs.<n>We propose tinyV, a lightweight LLM-based verifier that augments existing rule-based methods.
  arXiv  Detail & Related papers  (2025-05-20T17:16:44Z)
• SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [74.40683913645731]
  Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications.<n>Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth.<n>Analysis of these prompt scores reveals VLM biases and AND''/OR' signal ambiguities, notably that maximum scores are surprisingly suboptimal compared to second-highest scores.
  arXiv  Detail & Related papers  (2025-02-24T07:15:05Z)
• Rationale-Aware Answer Verification by Pairwise Self-Evaluation [11.763229353978321]
  We show that training reliable verifiers requires ensuring the validity of rationales in addition to the correctness of the final answers. Our results suggest that training reliable verifiers requires ensuring the validity of rationales in addition to the correctness of the final answers.
  arXiv  Detail & Related papers  (2024-10-07T08:53:00Z)
• Small Language Models Need Strong Verifiers to Self-Correct Reasoning [69.94251699982388]
  Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs) This work explores whether small (= 13B) language models (LMs) have the ability of self-correction on reasoning tasks with minimal inputs from stronger LMs.
  arXiv  Detail & Related papers  (2024-04-26T03:41:28Z)
• V-STaR: Training Verifiers for Self-Taught Reasoners [71.53113558733227]
  V-STaR trains a verifier using DPO that judges correctness of model-generated solutions. Running V-STaR for multiple iterations results in progressively better reasoners and verifiers.
  arXiv  Detail & Related papers  (2024-02-09T15:02:56Z)

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.