Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning

• URL: http://arxiv.org/abs/2602.03485v1
• Date: Tue, 03 Feb 2026 12:58:23 GMT
• Title: Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning
• Abstract summary: 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.
• Score: 27.979418392479033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Reasoning Models (LRMs) achieve strong performance by generating long reasoning traces with reflection. Through a large-scale empirical analysis, we find that a substantial fraction of reflective steps consist of self-verification (recheck) that repeatedly confirm intermediate results. These rechecks occur frequently across models and benchmarks, yet the vast majority are confirmatory rather than corrective, rarely identifying errors and altering reasoning outcomes. This reveals a mismatch between how often self-verification is activated and how often it is actually useful. Motivated by this, we propose a novel, experience-driven test-time framework that reduces the overused verification. Our method detects the activation of recheck behavior, consults an offline experience pool of past verification outcomes, and estimates whether a recheck is likely unnecessary via efficient retrieval. When historical experience suggests unnecessary, a suppression signal redirects the model to proceed. Across multiple model and benchmarks, our approach reduces token usage up to 20.3% while maintaining the accuracy, and in some datasets even yields accuracy improvements.

Related papers

• AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification [5.990350746292239]
  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.
  arXiv  Detail & Related papers  (2026-08-26T11:06:40Z)
• ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling [60.48279351544583]
  ThinkRetrieve is a test-time scaling framework for large reasoning models.<n>It retrieves relevant exemplars at each intermediate step and injects them directly into the thinking trace.<n>It consistently improves accuracy over standard test-time scaling.
  arXiv  Detail & Related papers  (2026-08-11T13:58:07Z)
• FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition [54.31138496553705]
  Fine-grained recognition in everyday life is often not a closed-book classification problem.<n>Existing benchmarks primarily evaluate visually recognition, leaving this active external knowledge acquisition ability underexplored.<n>We study fine-grained knowledge acquisition, where a system must seek, verify, and use external evidence to answer open-ended fine-grained recognition questions.
  arXiv  Detail & Related papers  (2026-05-13T08:49:51Z)
• Efficient Test-Time Scaling via Temporal Reasoning Aggregation [5.87118425760756]
  We propose TRACE, a training-free framework for efficient test-time scaling.<n>TRACE determines when to terminate reasoning based on temporal aggregation of multi-step evidence.<n>We show that TRACE reduces reasoning token usage by 25-30% on average while maintaining accuracy within 1-2% of full-length reasoning.
  arXiv  Detail & Related papers  (2026-04-19T07:39:40Z)
• Decoding the Critique Mechanism in Large Reasoning Models [50.821607345799386]
  Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions.<n>We investigate how current LRMs recover from errors by inserting arithmetic mistakes in their intermediate reasoning steps.<n>We find that despite the error propagating through the chain-of-thought, the model still reaches the correct final answer.
  arXiv  Detail & Related papers  (2026-03-17T10:03:30Z)
• interwhen: A Generalizable Framework for Verifiable Reasoning with Test-time Monitors [47.363850513075356]
  We present a test-time verification framework, interwhen, that ensures that the output of a reasoning model is valid wrt. a given set of verifiers.<n> Verified reasoning is an important goal in high-stakes scenarios such as deploying agents in the physical world.
  arXiv  Detail & Related papers  (2026-02-05T08:35:01Z)
• 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)
• Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models [5.408799241182959]
  We show that it regularizes model behavior during multi-step reasoning for Large Reasoning Models (LRMs)<n>We conduct a comprehensive study across 13 diverse benchmarks and observe that improves accuracy while substantially reducing reasoning token usage.<n>Surprisingly, we also observe emergent collective effects in batched inference: models often generalize patterns from earlier examples to solve harder ones.
  arXiv  Detail & Related papers  (2025-11-06T06:47:39Z)
• 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)
• Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning [53.05161493434908]
  Claim verification with large language models (LLMs) has recently attracted growing attention, due to their strong reasoning capabilities and transparent verification processes.<n>We introduce Veri-R1, an online reinforcement learning framework that enables an LLM to interact with a search engine and to receive reward signals that explicitly shape its planning, retrieval, and reasoning behaviors.<n> Empirical results show that Veri-R1 improves joint accuracy by up to 30% and doubles the evidence score, often surpassing its larger-scale model counterparts.
  arXiv  Detail & Related papers  (2025-10-02T11:49:48Z)
• Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers [63.99316853136304]
  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.
  arXiv  Detail & Related papers  (2025-09-27T06:50:24Z)
• 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)
• Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs [87.79350168490475]
  This work formally defines self-consistent errors and evaluates mainstream detection methods on them.<n>All four types of detection methods significantly struggle to detect self-consistent errors.<n>Motivated by the observation that self-consistent errors often differ across LLMs, we propose a simple but effective cross-model probe.
  arXiv  Detail & Related papers  (2025-05-23T09:18:56Z)
• When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits [5.443263983810103]
  As users interact with claims online, they often introduce edits, and it remains unclear whether current embedding models are robust to such edits.<n>We introduce a perturbation framework that generates valid and natural claim variations, enabling us to assess the robustness of a wide-range of sentence embedding models.<n>Our evaluation reveals that standard embedding models exhibit notable performance drops on edited claims, while LLM-distilled embedding models offer improved robustness at a higher computational cost.
  arXiv  Detail & Related papers  (2025-03-05T11:47:32Z)
• Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification [35.347715518778095]
  We study the scaling trends governing sampling-based search.<n>We find that simply scaling up a minimalist implementation of sampling-based search provides a practical inference method.<n>We identify two useful principles for improving self-verification capabilities with test-time compute.
  arXiv  Detail & Related papers  (2025-02-03T21:31:07Z)
• Scaling Flaws of Verifier-Guided Search in Mathematical Reasoning [16.824343439487617]
  Large language models (LLMs) struggle with multi-step reasoning, where inference-time scaling has emerged as a promising strategy for performance improvement.<n>Verifier-guided search outperforms repeated sampling when sample size is limited by selecting and prioritizing valid reasoning paths.<n>As sample size increases, verifier-guided search exhibits diminishing advantages and eventually underperforms repeated sampling.
  arXiv  Detail & Related papers  (2025-02-01T02:08:49Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning [55.76083560152823]
  SelfCheck is a general-purpose zero-shot verification schema for recognizing errors in step-by-step reasoning. We test SelfCheck on three datasets (GSM8K, MathQA, and MATH) and find that it successfully recognizes errors and, in turn, increases final answer accuracies.
  arXiv  Detail & Related papers  (2023-08-01T10:31:36Z)

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.