- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
SPLIT-RL separates visual perception and language reasoning during reinforcement learning to address the coarse credit assignment of final-answer rewards. It trains a single model first to produce useful image descriptions, then to reason from those descriptions without seeing the image. It also proposed CLA-GRPO, which assigns claim-level advantages by comparing the correctness of visual statements within groups of the same visual type. Across five backbones and six visual mathematics and logic benchmarks, SPLIT-RL improves average accuracy over GRPO by 1.4–6.1 points. Ablations validate the effectiveness of training perception before reasoning and combining completeness and correctness signals.
Critical strengths
-
SPLIT-RL separates perception from reasoning during training, making it easier to target the source of errors, and introduces claim-level advantages to distinguish correct and incorrect visual statements within the same description.
-
The experiments provide substantial evidence for both effectiveness and the proposed design choices. Improvements over GRPO are consistent across five backbones and six benchmarks, spanning different model sizes and architectures. Beyond aggregate accuracy, the ablations examine reward components and training order, while capability-specific diagnostics provide evidence that both perception and reasoning improve.
Critical weaknesses
- The performance gains may not justify the additional training cost. The paper does not provide a quantitative analysis of training efficiency. Based on the method description, SPLIT-RL appears substantially more expensive than vanilla GRPO: it involves two separate training stages, and CLA-GRPO additionally requires a visual judge. These components could increase training time and, depending on how the judge is deployed, memory requirements. The reported gains seem modest relative to this potential overhead.
- The evaluation is restricted to multimodal mathematical reasoning benchmarks and does not include perception-centric benchmarks. Given the method’s emphasis on improving perception, demonstrating its effectiveness on such benchmarks is essential.
- Minor problems: (1) Presentation: The figures could be improved, particularly Figure 2, where the small font makes the training pipeline and annotations difficult to read. (2) Missing relevant references: The related-work discussion omits several closely relevant studies. PTS: Unleashing Perception-Time Scaling to Multimodal Reasoning Models, which explores explicit perception decomposition and reinforcement learning for improving visual perception; CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning trains a captioning model using the accuracy of a text-only model answering questions from its captions, closely related to the proposed description bottleneck; ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison, which uses verified atomic claim differences to construct captioning rewards. Discussing these connections would help clarify SPLIT-RL’s novelty, particularly its staged optimization and claim-level advantage assignment.
Questions for authors
- How is the training efficiency of the SPLIT-RL?
- How is the SPLIT-RL's performance on more perception-centric multimodal benchmarks?
3 comments
Weakness 2:
Our original evaluation followed the benchmark suite used in PEARL [1] (CVPR 2026). However, we agree that direct evaluation of perception is important to show effectiveness of our method. To address this concern, we extend the evaluation to PerceptionBench [2] and MMStar [3]. PerceptionBench [1] evaluates atomic visual perception capabilities through questions designed to isolate perceptual ability from reasoning and external knowledge. MMStar [2] evaluates multimodal understanding through questions selected to require visual input, spanning coarse and fine-grained perception capabilities.
The results below use Qwen3-VL-8B as the backbone, with accuracy reported in percentages.
| Model | PerceptionBench | MMStar |
|---|---|---|
| Qwen3-VL-8B | 27.07 | 65.13 |
| GRPO | 25.60 | 65.00 |
| SPLIT-RL | 29.73 | 72.67 |
| Δ vs GRPO | 4.13 | 7.67 |
SPLIT-RL outperforms both GRPO and the base model on both benchmarks. Beyond its gains of 4.13 and 7.67 percentage points over GRPO, it improves over the base model by 2.66 and 7.54 points, respectively. GRPO decreases PerceptionBench accuracy relative to the base model and leaves MMStar performance essentially unchanged. This observation is consistent with our analysis in Fig. 1 that final-answer supervision alone does not necessarily improve visual perception. SPLIT-RL’s improvement on these two benchmarks shows that its benefits extend to atomic as well broader visual understanding.
[1] Chi Zhang et al. Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 41111–41120, 2026
[2] Zichao Lin et al. PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models. arXiv preprint arXiv:2607.24957, 2026.
[3] Lin Chen et al. Are We on the Right Way for Evaluating Large Vision-Language Models? Advances in Neural Information Processing Systems (NeurIPS), 2024
Weakness 3
We thank the reviewer for highlighting these presentation issues and relevant studies. We will revise Figure 2 by enlarging labels and annotations, allocating more space to the two training phases, and making the flow between visual description and language reasoning clearer. We will also check all figures at the final publication size to ensure readability.
We will add PTS [4], CapRL [5], and ClaimDiff-RL [6] to the related-work discussion and explicitly explain their connections to SPLIT-RL.PTS uses supervised training followed by RL to teach step-by-step visual measurement, such as estimating a target length through repeated comparisons with a reference segment. SPLIT-RL instead separates the optimization of visual description and language reasoning into dedicated training phases within a single policy. CapRL shares the description bottleneck, rewarding a captioner through a separate text-only model’s answer accuracy. SPLIT-RL additionally optimizes the answering capability of the same policy in its language reasoning phase. ClaimDiff-RL verifies atomic differences between generated and reference captions and aggregates them into a caption-level reward. SPLIT-RL uses claim verification to assign credit within each description: it normalizes each relevant claim’s correctness against claims of the same visual type across rollouts for the same question and applies the resulting advantage to that claim’s tokens.
[4] Yifan Li et al. Unleashing Perception-Time Scaling to Multimodal Reasoning Models. International Conference on Learning Representations (ICLR), 2026.
[5] Long Xing et al. CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning. International Conference on Learning Representations (ICLR), 2026.
[6] Tianle Li et al. ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison. arXiv preprint arXiv:2605.20278, 2026.
Questions to Authors
Q1: answered in weakness 1
Q2: answered in weakness 2
We hope this clarifies the reviewer’s concerns. We would be happy to answer any further questions or provide additional clarifications if needed.
We thank the reviewer for their valuable feedback and recognizing SPLIT-RL’s strengths of introducing fine-grained, capability-specific optimization, supported by consistent gains and comprehensive experimental validation. Below, we provide our response to address the concerns and questions.
weakness 1:
We provide the quantitative analysis of training efficiency below. SPLIT-RL improves average accuracy by 2.7 % while generating 54% fewer training tokens, at 1.75× the total GPU-hours. The breakdown identifies CLA judge waiting as the main source of the measured overhead. However, it is to be noted that our current implementation does not yet exploit large-scale batching of CLA judge requests. Larger batches and greater judge-side parallelism could reduce waiting time, and lowering idle GPU-hours.
Regarding the two-stage design, SPLIT-RL allocates the same combined maximum output-token budget as GRPO: 2,048 tokens per stage versus 4,096 tokens for GRPO. Its actual generated-token count is substantially lower compared to GRPO, decreasing from 1,267M to 586M.
CLA supervision does introduce additional overhead, which we include in the reported GPU-hours (total). Specifically, waiting for the CLA judge accounts for 121 of SPLIT-RL’s 262 GPU-hours. Excluding this waiting time, SPLIT-RL uses 141 GPU-hours, compared with 150 for GRPO, a 6% reduction. Additionally, judge calls are deployed through API calls avoiding any additional GPU memory requirements.
In summary, SPLIT-RL additional training cost is a trade-off for fine-grained supervision that achieves higher accuracy with substantially fewer generated tokens. We will update our manuscript with these results.