Bad Seeing or Bad Thinking? Rewarding Perception for Vision-Language Reasoning

• URL: http://arxiv.org/abs/2605.14054v1
• Date: Wed, 13 May 2026 19:23:53 GMT
• Title: Bad Seeing or Bad Thinking? Rewarding Perception for Vision-Language Reasoning
• Abstract summary: We argue that the root cause of this trade-off is an ambiguity in modality credit assignment.<n>We introduce a reinforcement learning framework that improves perception-reasoning synergy.
• Score: 45.319525299206866
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or agentic workflows. However, these approaches are often limited by static textual reasoning or complicated by the significant compute and engineering burden of external agentic complexity. Worse, this heavy investment does not yield proportional gains, often witnessing a "seesaw effect" on perception and reasoning. This motivates a fundamental rethinking of the true bottleneck. In this paper, we argue that the root cause of this trade-off is an ambiguity in modality credit assignment: when a VLM fails, is it due to flawed perception ("bad seeing") or flawed logic ("bad thinking")? To resolve this, we introduce a reinforcement learning framework that improves perception-reasoning synergy by reliably rewarding the perception fidelity. We explicitly decompose the generation process into interleaved perception and reasoning steps. This decoupling enables targeted supervision on perception. Crucially, we introduce Perception Verification (PV), leveraging a "blindfolded reasoning" proxy to reward perceptual fidelity independently of reasoning outcomes. Furthermore, to scale training across free-form VL tasks, we propose Structured Verbal Verification, which replaces high-variance LLM judging with structured algorithmic execution. These techniques are integrated into a Modality-Aware Credit Assignment (MoCA) mechanism, which routes rewards to the specific source of error -- either bad seeing or bad thinking -- enabling a single VLM to achieve simultaneous performance gains across a wide task spectrum.

Related papers

• ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation [71.69632267962993]
  We argue that manipulation planning naturally decomposes into prediction, anticipating the next visual state, and inverse dynamics.<n>We propose textbfThinkingVLA, a generative model that realizes this decomposition within a unified Mixture-of-Transformers architecture.<n>Experiments on simulation and real-world benchmarks demonstrate that ThinkingVLA consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T13:45:17Z)
• Can VLMs Reason Robustly? A Neuro-Symbolic Investigation [24.000218548502875]
  Vision-Language Models (VLMs) have been applied to a wide range of reasoning tasks.<n>It remains unclear whether they can reason robustly under distribution shifts.<n>We propose a neuro-symbolic method that combines VLM-based concept recognition with circuit-based symbolic reasoning.
  arXiv  Detail & Related papers  (2026-03-25T02:48:42Z)
• Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation [46.38008143057758]
  Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.<n>This work argues that reward modeling is not merely an implementation detail but a central architect of reasoning alignment.<n>Within this framework, we present a taxonomy of reward mechanisms, analyze reward hacking as a pervasive failure mode, and examine how reward signals unify challenges.
  arXiv  Detail & Related papers  (2026-02-10T00:45:24Z)
• Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning [50.352417879912515]
  Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities.<n>We propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns.<n>We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust.
  arXiv  Detail & Related papers  (2026-02-06T08:03:11Z)
• ALIVE: Awakening LLM Reasoning via Adversarial Learning and Instructive Verbal Evaluation [4.265094703231012]
  We introduce textbfALIVE (emphAdrial Learning with Instructive Verbal Evaluation), a hands-free alignment framework.<n>By coupling adversarial learning with instructive verbal feedback, ALIVE enables models to internalize evaluative criteria directly from raw corpora.<n>With identical data and compute, ALIVE achieves markedly improved cross-domain generalization, and higher self-correction rates.
  arXiv  Detail & Related papers  (2026-02-05T09:20:23Z)
• Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization [56.59356959631999]
  Gated Perception-Reasoning Optimization (GPRO) is a meta-reasoning controller that dynamically routes computation among three decision paths.<n>GPRO substantially improves both accuracy and efficiency, outperforming recent slow-thinking methods.
  arXiv  Detail & Related papers  (2026-01-07T23:05:17Z)
• Cognitive Inception: Agentic Reasoning against Visual Deceptions by Injecting Skepticism [81.39177645864757]
  We propose textbfInception, a fully reasoning-based agentic reasoning framework to conduct authenticity verification by injecting skepticism.<n>To the best of our knowledge, this is the first fully reasoning-based framework against AIGC visual deceptions.
  arXiv  Detail & Related papers  (2025-11-21T05:13:30Z)
• GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training [62.536191233049614]
  Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs)<n>This work investigates this problem through extensive experiments on complex card games, such as 24 points, and embodied tasks from ALFWorld.<n>We find that when rewards are based solely on action outcomes, RL fails to incentivize CoT reasoning in VLMs, instead leading to a phenomenon we termed thought collapse.
  arXiv  Detail & Related papers  (2025-03-11T15:17:02Z)

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.