- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces VisualReasoningGym, an adaptive and verifiable data generation framework for multimodal compositional reasoning. The authors argue that traditional visual question-answering datasets rely on fixed image-question-answer triplets, whose effectiveness in providing meaningful reinforcement learning signals may diminish as model capabilities evolve.
To address this issue, VisualReasoningGym transforms existing images and annotations into environments that dynamically generate new questions. Specifically, the framework constructs visually grounded atomic questions from images and their metadata, and then combines these questions into more complex reasoning tasks using executable symbolic programs. Furthermore, the framework dynamically adjusts task difficulty based on the model's rollout performance to maintain effective training signals for reinforcement learning with verifiable rewards (RLVR).
The authors also introduce VisualGym-Ladder, a benchmark that evaluates compositional reasoning capabilities across eight progressively increasing difficulty levels. Experimental results demonstrate substantial improvements in the compositional reasoning performance of Qwen3-VL-8B-Thinking, along with positive transfer to several external visual reasoning benchmarks.
Critical strengths
-
The paper identifies an important issue in RLVR training, where static visual question-answering datasets may gradually lose their effectiveness in providing meaningful learning signals. The authors further investigate this phenomenon across different models and training stages, making the research motivation practically relevant.
-
By decomposing existing visual data into atomic questions and recombining them, the proposed framework can generate reasoning tasks at different difficulty levels without requiring additional image generation. This improves the utilization of existing visual datasets and annotations.
-
The proposed method achieves substantial improvements on VisualGym-Ladder and demonstrates positive transfer to several external visual reasoning benchmarks. The ablation studies and experiments across different models further support the effectiveness of the approach.
Critical weaknesses
-
Insufficient discussion of related work. The paper lacks a comprehensive discussion of closely related studies, including COGS [1], Composition-RL [2], SynthRL [3], and DIVA-GRPO [4]. These works are closely related to the proposed approach in terms of compositional question generation, verifiable data synthesis, or adaptive reinforcement learning.
-
Unclear novelty relative to existing methods. Long Grounded Thoughts [5] has already explored generating verifiable compositional visual reasoning problems from existing images. Although this work is cited, the paper lacks an in-depth comparison with it. The authors should more clearly distinguish their technical contributions from existing approaches and consider discussing Bee [6] and other relevant studies on multimodal data construction.
-
Insufficient validation of automatically generated data quality. The atomic questions rely on VLM-generated metadata and automatic annotations, which may introduce incorrect supervision signals. In particular, converted questions are retained if at least one out of five verification attempts succeeds. The authors are encouraged to provide human evaluation of annotation quality and ablation studies using stricter filtering criteria.
-
Limited evaluation of compositional generalization. The training and evaluation stages use the same families of symbolic reasoning programs, making it unclear whether the model can generalize to unseen compositional patterns. Furthermore, the current experiments do not sufficiently disentangle improvements in atomic visual perception from improvements in symbolic reasoning capabilities.
[1] Gu et al. Composition-Grounded Data Synthesis for Visual Reasoning. ICLR 2026. https://proceedings.iclr.cc/paper_files/paper/2026/hash/4733cee6af505d5e2782a1dc499c0d7e-Abstract-Conference.html
[2] Xu et al. Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models. arXiv:2602.12036, 2026. https://arxiv.org/abs/2602.12036
[3] Wu et al. SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis. Findings of ACL 2026. https://aclanthology.org/2026.findings-acl.2107/
[4] Gao et al. DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage. ICLR 2026. https://proceedings.iclr.cc/paper_files/paper/2026/hash/3adaa3ccd68cf934455f871f95cc95de-Abstract-Conference.html
[5] Acuna et al. Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale. ICML 2026. https://proceedings.mlr.press/v306/acuna26a.html
[6] Zhang et al. Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs. ICLR 2026. https://proceedings.iclr.cc/paper_files/paper/2026/hash/171291d8fed723c6dfc76330aa827ff8-Abstract-Conference.html
Questions for authors
same with weaknesses.
3 comments
Thanks for the rebuttal. My main remaining question is whether the gains extend to program families unseen during training. The improvement on atomic questions is helpful to see, but it is still unclear how much of the gain comes from better visual perception and how much comes from better composition. The human audit addresses the quality of the evaluation labels, while the effect of stricter filtering on training remains open.
Thank you for the follow-up. All three points are fair. We address each one below in details.
1. Unseen program families. This is a good idea. We have not tested this in-domain. Training and the ladder use the same program families, and the ladder holds out images, not families. We will add this experiment to the final version. That said, the external benchmarks are popular multimodal benchmarks not generated by our programs, and 11 of 14 improve, including CharXiv (+3.24), ChartQAPro (+2.23) and BabyVision (+4.82).
2. Perception versus composition. Our evidence points to both, but it does not separate them exactly. We split the saved VisualGym-Ladder responses (Table 1 runs, D1–D7, no new inference) by program. Accuracy in %:
| Program | Ladders | Base | + Text-only | + D0-only | + Ours | Ours − Base (95% CI) |
|---|---|---|---|---|---|---|
| Sum, min, max | 12 | 69.5 | 74.8 | 76.0 | 90.2 | +20.7 (6.4 to 37.1) |
| All other programs | 88 | 42.8 | 47.9 | 46.4 | 67.0 | +24.2 (19.3 to 29.3) |
- Perception: single questions (D0) improve from 77.4% to 89.4%, and atomic answers inside composed responses improve from 78.6% to 88.6%.
- Composition: on the other programs Base scores 42.8% and our model reaches 67.0%, while training on symbolic questions without images (Text-only) or on single visual questions (D0-only) reaches only 47.9% and 46.4%.
An exact split needs an evaluation with the correct sub-answers given as text. We will add it to the final version.
3. Stricter filtering for training. This is still open. The training labels come from the same pipeline as the audited labels (2.17% marked incorrect). As stated in the paper (Appendix B.2), converted source questions (except DeltaPrompts) are kept only if an independent model answers them correctly in at least one of five trials. We will retrain with a three-of-five screen and report the result.
Thank you for the supportive review and for the references; we will add them to the related work.
Related work and contribution
Our contribution is the finding that fixed visual questions can lose training value, together with a reusable generator that adapts to the base model and to the same policy as it improves. The adaptation takes place in the generated tasks, with the RL update rule unchanged. We evaluate this design through adaptive training, composition ladders, and transfer to external benchmarks. We will expand the related-work discussion to make these connections and distinctions explicit.
Data quality
Following your suggestion, we ran a human audit; the results are in the general response above. Removing the five affected image ladders produces negligible changes in pass@5 proficiency and preserves the ordering of the five reported models. We will filter the final release using human annotations. The one-of-five conversion rule is a screening threshold. Our filtering check tests evaluation robustness; we have not retrained with a stricter conversion filter but will add this to the final version.
Generalization and the source of improvement
We evaluate transfer beyond the generated tasks: performance improves in 11 of 14 external settings, with the mean rising from 52.69% to 56.34%. Within composed D1–D7 responses, atomic accuracy on matched extracted answers rises from 78.6% to 88.6%. These results support better intermediate answers and transfer to external benchmark tasks, which use their own questions and answer formats. The original 100-image VisualGym-Ladder holds out images within known program families; we did not hold out program families, so the external benchmarks are our evidence for transfer beyond them.