Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs

• URL: http://arxiv.org/abs/2512.06258v1
• Date: Sat, 06 Dec 2025 03:02:55 GMT
• Title: Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs
• Authors: Chaoyang Wang, Yangfan He, Yiyang Zhou, Yixuan Wang, Jiaqi Liu, Peng Xia, Zhengzhong Tu, Mohit Bansal, Huaxiu Yao,
• Abstract summary: We reveal a critical yet underexplored flaw in Large Vision-Language Models (LVLMs)<n>Even when these models know the correct answer, they frequently arrive there through incorrect reasoning paths.<n>We propose PSO (Path-Select Optimization), a two-stage post-training framework designed to enhance both the reasoning performance and stability of existing LVLMs.
• Score: 85.37131922131657
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We reveal a critical yet underexplored flaw in Large Vision-Language Models (LVLMs): even when these models know the correct answer, they frequently arrive there through incorrect reasoning paths. The core issue is not a lack of knowledge, but a path selection bias within the vast reasoning search space. Although LVLMs are often capable of sampling correct solution trajectories, they disproportionately favor unstable or logically inconsistent ones, leading to erratic and unreliable outcomes. The substantial disparity between Pass@K (with large K) and Pass@1 across numerous models provides compelling evidence that such failures primarily stem from misreasoning rather than ignorance. To systematically investigate and address this issue, we propose PSO (Path-Select Optimization), a two-stage post-training framework designed to enhance both the reasoning performance and stability of existing LVLMs. In the first stage, we employ Group Relative Policy Optimization (GRPO) with template and answer-based rewards to cultivate structured, step-by-step reasoning. In the second stage, we conduct online preference optimization, where the model samples reasoning paths from GRPO-generated data, self-evaluates them, and aligns itself toward the preferred trajectories. Incorrect or suboptimal paths are concurrently stored in a Negative Replay Memory (NRM) as hard negatives, which are periodically revisited to prevent the model from repeating prior mistakes and to facilitate continual reasoning refinement. Extensive experiments show that PSO effectively prunes invalid reasoning paths, substantially enhances reasoning accuracy (with 7.4% improvements on average), and yields more stable and consistent chains of thought. Our code will be available at https://github.com/aiming-lab/PSO.

Related papers

• Learn Hard Problems During RL with Reference Guided Fine-tuning [56.56461712665904]
  Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity.<n>We introduce Reference-Guided Fine-Tuning (ReGFT) to synthesize positive trajectories on hard problems and train on them before RL.<n>Our results show that ReGFT effectively overcomes reward sparsity and unlocks stronger RL-based mathematical reasoning.
  arXiv  Detail & Related papers  (2026-03-01T18:41:28Z)
• Probing the Trajectories of Reasoning Traces in Large Language Models [4.599673637363014]
  We propose a protocol to probe the trajectories of reasoning traces in large language models.<n>We find that accuracy and decision commitment consistently increase as the percentage of provided reasoning tokens grows.<n>We show that trajectory probing provides diagnostics for efficient and safer deployment of reasoning models.
  arXiv  Detail & Related papers  (2026-01-30T16:45:16Z)
• Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning [59.76691952347156]
  Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs)<n>Most existing RL approaches rely on sparse outcome rewards, which fail to credit correct intermediate steps in partially successful solutions.<n>We propose Verifiable Prefix Policy Optimization (VPPO), which uses PRMs only to localize the first error during RL.
  arXiv  Detail & Related papers  (2026-01-26T21:38:20Z)
• InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning [32.274434679047395]
  Outcome-reward reinforcement learning (RL) has proven effective at improving the reasoning capabilities of large language models (LLMs)<n>Standard RL assigns credit only at the level of the final answer, penalizing entire reasoning traces when the outcome is incorrect.<n>We introduce Intervention Training (InT), a training paradigm in which the model performs fine-grained credit assignment on its own reasoning traces.
  arXiv  Detail & Related papers  (2026-01-20T18:15:38Z)
• Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models [61.55758048622473]
  We introduce Neural Chain-of-Thought Search (NCoTS), a framework that reformulates reasoning as a dynamic search for the optimal thinking strategy.<n>By quantitatively characterizing the solution space, we reveal the existence of sparse superior reasoning paths that are simultaneously more accurate and concise than standard outputs.
  arXiv  Detail & Related papers  (2026-01-16T14:38:18Z)
• Hard Negative Sample-Augmented DPO Post-Training for Small Language Models [4.425580048633862]
  We propose a lightweight and pragmatic post-training pipeline that targets structured errors under realistic compute budgets.<n>We introduce a compact MathVerifier that decomposes a candidate solution into a six-dimensional error profile and aggregates it into interpretable wrongness and absurdity scores.<n> Experiments show that verifier-guided, weighted DPO yields more targeted improvements than vanilla SFT and unweighted DPO.
  arXiv  Detail & Related papers  (2025-12-17T06:15:52Z)
• Verifying Large Language Models' Reasoning Paths via Correlation Matrix Rank [71.09032766271493]
  Large language models (LLMs) are prone to errors and hallucinations.<n>How to check their outputs effectively and efficiently has become a critical problem in their applications.
  arXiv  Detail & Related papers  (2025-10-28T11:01:10Z)
• FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning [42.18368547352248]
  Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models (LLMs)<n>We propose Flawed-Aware Policy Optimization (FAPO), which presents a parameter-free reward penalty for flawed-positive rollouts.<n>Experiments show that FAPO is effective in broad domains, improving outcome correctness, process reliability, and training stability without increasing the token budget.
  arXiv  Detail & Related papers  (2025-10-26T05:49:38Z)
• Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning [14.57256913655025]
  We propose Cog-Rethinker, a novel hierarchical metacognitive RL framework for LLM reasoning.<n>Our Cog-Rethinker mainly focuses on the rollout procedure in RL training.<n>By leveraging human cognition during solving problems, it prompts policy to decompose zero-accuracy problems into subproblems.
  arXiv  Detail & Related papers  (2025-10-13T08:16:21Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding [59.60915947702282]
  Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs)<n>Existing RLVR methods often suffer from exploration inefficiency due to mismatches between the training data's difficulty and the model's capability.<n>We propose SEELE, a novel supervision-aided RLVR framework that dynamically adjusts problem difficulty to stay within the high-efficiency region.
  arXiv  Detail & Related papers  (2025-09-08T17:36:21Z)
• Explicit Preference Optimization: No Need for an Implicit Reward Model [18.225409932618657]
  Direct preference optimization (DPO) and its offshoots circumvent the need for a separate reward training step.<n>We show that DPO-based objectives are nonetheless subject to sub-optimal regularization and counter-intuitive artifacts.
  arXiv  Detail & Related papers  (2025-06-09T07:11:01Z)
• Self-Training Large Language Models with Confident Reasoning [15.260831996769962]
  Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers.<n>We propose a new self-training method, CORE-PO, that fine-tunes LLMs to prefer high-COnfidence REasoning paths through Policy Optimization.<n>Our experiments show that CORE-PO improves the accuracy of outputs on four in-distribution and two out-of-distribution benchmarks, compared to existing self-training methods.
  arXiv  Detail & Related papers  (2025-05-23T04:25:10Z)
• Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models [67.87579664988199]
  TON is a two-stage training strategy for vision-language models (VLMs)<n>It introduces a think-or-not format that serves as a cold start for selective reasoning.<n>TON can reduce the completion length by up to 90% compared to vanilla GRPO.
  arXiv  Detail & Related papers  (2025-05-22T16:13:29Z)
• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)

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.