- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies why reinforcement learning (RL) improves some vision-language tasks more than others by separating perception and reasoning bottlenecks. It proposes PARA to diagnose perception and reasoning headroom at the model–benchmark level. Based on the analysis, it proposes GRAD, an attention-distillation method that directly improves visual perception during RL.
Critical strengths
- PARA quantifies how much model error can be recovered by better perception versus better reasoning, showing that the dominant bottleneck depends on the specific model–benchmark pair, rather than the benchmark category alone. The analysis further reveals that current RL benefits more from reasoning headroom than perception headroom, providing a clear explanation for the uneven gains of visual RL.
- Based on the finding that reward- and token-level signals affect visual attention only indirectly, the paper proposes GRAD to distill attention from the best rollout within each group into weaker rollouts. GRAD consistently improves performance across two model scales and seven benchmarks and outperforms standard GRPO and other perception-oriented baselines on average.
Critical weaknesses
- PARA does not fully disentangle perception and reasoning. A recovered sample under the perceptual intervention still depends on the target model’s ability to reason over the oracle caption, so may capture both improved visual information and easier text-based reasoning rather than perception alone. A cleaner design would explicitly decompose each sample into image → visual facts → QA, so perception and reasoning can be evaluated independently.
- The logic from Sec. 4 to GRAD is not fully justified. Sec. 4 mainly shows cross-benchmark correlations, while GRAD assumes that the highest-reward sibling provides better visual attention, even though the paper itself argues that outcome reward conflates perception and reasoning.
Questions for authors
- Could PARA be interpreted more conservatively as measuring a benchmark’s sensitivity to different forms of additional information, rather than directly identifying the true failure source?
- Can the authors justify the bottleneck analysis at the sample level rather than only at the benchmark level? A single benchmark may contain both perception-focused and reasoning-focused questions, so an aggregate headroom score may hide substantial within-benchmark variation; a per-sample attribution or grouping by visual-information dependence could provide stronger evidence for the claimed bottlenecks.
- The model-specific bottleneck claim may be confounded by model-family differences. Since the evaluated models come from different families, differences in training data, architecture, or prior knowledge may affect the measured headroom, not just perception/reasoning ability. Would comparing different model sizes within the same model family provide a cleaner analysis of how perception and reasoning headroom change with model capacity?
- For GRAD, is the highest-reward sibling necessarily the one with better visual attention? A direct grounding or attention-quality analysis would strengthen this assumption.
- Missing related works. For example, No-Thinking-RFT[1], ReFine-RFT[2], MoCA[3], and Chain-of-Thought Degrades Visual Spatial Reasoning, and Look Light, Think Heavy [4].
[1]: Li M, Zhong J, Zhao S, et al. To think or not to think: A study of thinking in rule-based visual reinforcement fine-tuning[J]. Advances in Neural Information Processing Systems, 2026, 38: 167356-167407. [2]: Zhu J, Su Y, Liu X. Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?[J]. arXiv preprint arXiv:2601.06993, 2026. [3]: Wang H, Xu Q, Wang C, et al. Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning[J]. arXiv preprint arXiv:2605.14054, 2026. [4]: Kancheti S S, Kanade A S, Balasubramanian V N, et al. Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs[C]//Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2026: 862-876.
2 comments
We sincerely appreciate the reviewer's thoughtful feedback and positive assessment of our work. We are grateful for the constructive suggestions, which have helped us strengthen the paper. Thank you again for your time and engagement throughout the discussion.
Response to Author's Rebuttal
Thank you for the detailed reply. I maintain my positive rating.