Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?

• URL: http://arxiv.org/abs/2506.17417v1
• Date: Fri, 20 Jun 2025 18:23:48 GMT
• Title: Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?
• Abstract summary: We investigate whether inference-time techniques extend effectively to vision-reliant models (VLMs)<n>We find that while decoding strategies such as majority voting and best-of-N selection with self-verification all improve VLM reasoning performance, generation methods such as the former achieve significantly higher gains versus verification methods such as the latter.<n>We show via extensive experimentation within the inference-time scaling framework to identify a key root cause: RL-trained VLMs still lack robust self-verification capabilities across both visual and textual modalities.
• Score: 19.422376032675572
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in large language models (LLMs) have demonstrated that inference-time computation techniques, such as decoding-time scaling and self-refinement, can significantly enhance reasoning capabilities without relying on external knowledge. A key driver of this success is the emergence of self-correction and self-verification behaviors, often elicited through reinforcement learning (RL). In this paper, we investigate whether these inference-time techniques extend effectively to vision-language models (VLMs), particularly those trained with RL. We find that while decoding strategies such as majority voting and best-of-N selection with self-verification all improve VLM reasoning performance, generation-reliant methods such as the former achieve significantly higher gains versus verification-reliant methods such as the latter. Additionally, the self-correction behavior often associated with RL-tuned models, such as aha moment, does not lead to measurable gains. We show via extensive experimentation within the inference-time scaling framework to identify a key root cause: RL-trained VLMs still lack robust self-verification capabilities across both visual and textual modalities.

Related papers

• On Test-Time Scaling for Vision-Language Models [28.89310866658917]
  We present the first comprehensive study of test-time scaling for Large Vision-Language Models (LVLMs)<n>Our main findings are that small, well-performing models benefit the most from test-time scaling, enabling performance improvements of up to around 30%.<n>Visual information is encoded early in the reasoning chain, after which the chain is dominated by text-only reasoning and the contribution of image tokens drops significantly.
  arXiv  Detail & Related papers  (2026-06-27T11:12:42Z)
• Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models [129.8880969196575]
  We present an empirical analysis of attention in Diffusion large language models (dLLMs)<n>We show that tokens attending more strongly to unmasked context exhibit greater generation stability and play a critical role in reasoning.<n>Motivated by these findings, we propose AGDO, an attention-guided denoising and optimization framework.
  arXiv  Detail & Related papers  (2026-06-10T16:14:23Z)
• Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models [51.45122910254346]
  Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models beyond the training domain.<n>Supervised fine-tuning (SFT) frequently leads to general forgetting capabilities.<n>We present a feature-level mechanistic analysis methodology to probe RL generalization using a controlled experimental setup.
  arXiv  Detail & Related papers  (2026-04-27T21:22:34Z)
• Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification [55.357038267439684]
  Visual Re-Examination (VRE) is a self-evolving training framework that enables MLLMs to autonomously perform visual introspection during reasoning without additional visual inputs.<n>VRE consistently improves reasoning accuracy and perceptual reliability, while substantially reducing hallucinations, especially in long-chain settings.
  arXiv  Detail & Related papers  (2026-03-27T12:22:13Z)
• VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models [21.438802784706994]
  We propose VisRef, a visually grounded test-time scaling framework.<n>Our key idea is to actively guide the reasoning process by re-injecting a coreset of visual tokens.<n>Under fixed test-time compute budgets, VisRef consistently outperforms existing test-time scaling approaches by up to 6.4%.
  arXiv  Detail & Related papers  (2026-02-27T11:48:19Z)
• PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding [85.22047087898311]
  We introduce Polarity-Prompt Contrastive Decoding (PromptCD), a test-time behavior control method that generalizes contrastive decoding to broader enhancement settings.<n>PromptCD constructs paired positive and negative guiding prompts for a target behavior and contrasts model responses to reinforce desirable outcomes.<n>Experiments on the "3H" alignment objectives demonstrate consistent and substantial improvements, indicating that post-trained models can achieve meaningful self-enhancement purely at test time.
  arXiv  Detail & Related papers  (2026-02-24T08:56:52Z)
• Found-RL: foundation model-enhanced reinforcement learning for autonomous driving [15.275134927543611]
  Reinforcement Learning (RL) has emerged as a dominant paradigm for end-to-end autonomous driving (AD)<n>Found-RL is a platform tailored to efficiently enhance RL for AD using foundation models.<n>A core innovation is the asynchronous batch inference framework, which decouples heavy VLM reasoning from the simulation loop.
  arXiv  Detail & Related papers  (2026-02-11T02:56:04Z)
• Vision-aligned Latent Reasoning for Multi-modal Large Language Model [82.26044667101011]
  Vision-aligned Latent Reasoning (VaLR) is a framework that dynamically generates vision-aligned latent tokens before each Chain of Thought reasoning step.<n>VaLR is trained to preserve visual knowledge during reasoning by aligning intermediate embeddings of MLLM with those from vision encoders.
  arXiv  Detail & Related papers  (2026-02-04T12:04:02Z)
• Limits and Gains of Test-Time Scaling in Vision-Language Reasoning [8.76012279865596]
  Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning ability of Large Language Models (LLMs) by allocating additional computation at inference.<n>We present a systematic empirical study of inference time reasoning methods applied across both open-source and closed-source Vision-Language Models (VLMs) on different benchmarks.
  arXiv  Detail & Related papers  (2025-12-11T20:48:54Z)
• Unleashing Perception-Time Scaling to Multimodal Reasoning Models [60.578179197783754]
  Recent advances in inference-time scaling have substantially enhanced the reasoning capabilities of Large Vision-Language Models (LVLMs)<n>Inspired by this success, similar strategies have been applied to multimodal reasoning, yet their impact on visual perception remains unclear.<n>We propose Perception-Time Scaling (PTS), a novel paradigm that encourages token-rich perception and decomposes complex perception problems into intermediate tractable sub-problems.
  arXiv  Detail & Related papers  (2025-10-10T03:17:52Z)
• ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models [102.4511331368587]
  ARISE (Adaptive Resolution-aware Scaling Evaluation) is a novel metric designed to assess the test-time scaling effectiveness of large reasoning models.<n>We conduct comprehensive experiments evaluating state-of-the-art reasoning models across diverse domains.
  arXiv  Detail & Related papers  (2025-10-07T15:10:51Z)
• ReVeal: Self-Evolving Code Agents via Iterative Generation-Verification [6.983144806500892]
  ReVeal is a multi-turn reinforcement learning framework that interleaves code generation with explicit self-verification and tool-based evaluation.<n>It fosters the co-evolution of a model's generation and verification capabilities through RL training, expanding the reasoning boundaries of the base model.<n>It also enables test-time scaling into deeper inference regimes, with code consistently evolving as the number of turns increases during inference.
  arXiv  Detail & Related papers  (2025-06-13T03:41:04Z)
• Incentivizing LLMs to Self-Verify Their Answers [20.2584779107763]
  Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks.<n>We propose a framework that incentivizes LLMs to self-verify their own answers.<n>We train our self-verification models based on Qwen2.5-Math-7B and DeepSeek-R1-Distill-Qwen-1.5B.
  arXiv  Detail & Related papers  (2025-06-02T06:54:29Z)
• Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models [83.24079543652253]
  Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization.<n>However, reasoning-oriented RL fine-tuning significantly increases the prevalence of hallucinations.<n>We propose Factuality-aware Step-wise Policy Optimization (FSPO), an innovative RL fine-tuning algorithm incorporating explicit factuality verification.
  arXiv  Detail & Related papers  (2025-05-30T14:23:32Z)
• Can Large Reasoning Models Self-Train? [58.953117118687096]
  Scaling the performance of large language models increasingly depends on methods that reduce reliance on human supervision.<n>We propose an online self-training reinforcement learning algorithm that leverages the model's self-consistency to infer correctness signals and train without any ground-truth supervision.
  arXiv  Detail & Related papers  (2025-05-27T17:16:00Z)
• Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards [67.86091419220816]
  Large Language Models (LLMs) show great promise in complex reasoning.<n>A prevalent issue is superficial self-reflection'', where models fail to robustly verify their own outputs.<n>We introduce RISE (Reinforcing Reasoning with Self-Verification), a novel online RL framework designed to tackle this.
  arXiv  Detail & Related papers  (2025-05-19T17:59:31Z)
• Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme [36.34443944082215]
  This work introduces a transparent, from-scratch framework forReinforcement learning (RL) in vision-based models (VLMs)<n>It offers a minimal yet functional four-step pipeline validated across multiple models and datasets.<n>In addition, a standardized evaluation scheme is proposed to assess training dynamics and reflective behaviors.
  arXiv  Detail & Related papers  (2025-04-03T13:53:28Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [65.31658824274894]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models.<n>We propose self-certainty, a novel and efficient metric to estimate response quality without requiring external reward models.<n>Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)
• ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification [53.80183105328448]
  Refine via Intrinsic Self-Verification (ReVISE) is an efficient framework that enables LLMs to self-correct their outputs through self-verification.<n>Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.
  arXiv  Detail & Related papers  (2025-02-20T13:50:02Z)
• Self-Improvement in Language Models: The Sharpening Mechanism [70.9248553790022]
  We offer a new perspective on the capabilities of self-improvement through a lens we refer to as sharpening.<n>Motivated by the observation that language models are often better at verifying response quality than they are at generating correct responses, we formalize self-improvement as using the model itself as a verifier during post-training.<n>We analyze two natural families of self-improvement algorithms based on SFT and RLHF.
  arXiv  Detail & Related papers  (2024-12-02T20:24:17Z)
• Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks [43.96835245022083]
  Self-correction that instructs models to refine their outputs presents a promising solution to this issue.<n>This study investigates the self-correction capabilities of Vision-Language Models during both inference and fine-tuning stages.
  arXiv  Detail & Related papers  (2024-10-05T06:28:54Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)

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.