- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes RISE, a self-evolving training framework for vision-language models, aiming to address delayed feedback updates, degradation in generated question quality, and insufficient task diversity in existing dual-role self-evolving methods. The framework leverages unlabeled images to construct self-supervised training signals through alternating optimization of a questioner and a solver. Specifically, Fine-grained Role Alternation divides longer role-training phases into multiple shorter cycles to accelerate feedback between question generation and solving capabilities. Quality Supervisor reuses the current solver as a supervision model to assess the validity of generated questions and the reliability of pseudo-labels. Skill-aware Dynamic Balancing adjusts rewards according to the generation frequency of different skill categories and maintains training data diversity through stratified sampling. The authors conduct experiments on Qwen2.5-VL-7B and Qwen3-VL-8B using the Vision-47K image collection, optimizing the questioner and solver separately through GRPO. Across seven multimodal understanding and reasoning benchmarks, after 60 steps of self-evolving training, the weighted average scores of the two models improve from 48.17 to 52.26 and from 53.38 to 57.37, respectively. The paper further validates the contributions of the proposed components through ablation studies, generated data analysis, and repeated training experiments.
Critical strengths
-
Table 2 in Section 5.3 shows that, on Qwen2.5-VL-7B, when fine-grained role alternation is applied without quality supervision, the average score decreases from 50.43 at Step 20 to 44.85 at Step 60, even falling below the initial model's score of 48.17. After introducing quality supervision, the same setting achieves a score of 51.71 at Step 60. Together with the changes in generated question quality and skill distribution shown in Figure 3, these results provide concrete evidence of quality degradation during self-evolving training and demonstrate the practical role of quality control in maintaining training stability. The paper designs corresponding mechanisms around problems observed during training, establishing a meaningful connection between the research motivation and experimental analysis.
-
Table 1 shows that RISE achieves an overall improvement of approximately 4 percentage points on two different versions of Qwen-VL models, with gains on multimodal reasoning tasks such as MathVerse and MathVision. Appendix C.4 further validates the contributions of the three components on Qwen3-VL-8B, while Appendix C.5 reports an average score of 57.44 with a standard deviation of 0.28 across five independent runs. In addition, the authors reproduce VisPlay as a controlled baseline and examine part of the experimental results using benchmark-specific evaluation rules in Appendix C.6. These experiments provide relatively strong support for the effectiveness of the method and the stability of the reported results.
Critical weaknesses
-
Section 4.4.1 constructs the question difficulty reward based on the consistency of the solver's answers, but this design cannot reliably distinguish genuinely challenging reasoning questions from ambiguous ones. According to Equations (9) and (10), when 5 out of 10 sampled responses produce the same answer, the difficulty score reaches its maximum value of 0.5. However, such disagreement may arise either because a question is near the model's capability boundary or because the question is poorly specified or lacks sufficient visual evidence. More importantly, Equation (11) only incorporates question validity as a reward term with a weight of 0.2, without imposing a hard constraint on semantically invalid questions. This means that an invalid question with a high difficulty score may still receive a higher reward than a simple but valid question. Although the subsequent data filtering process checks question validity, it cannot completely eliminate the incorrect incentives introduced during questioner training. Therefore, more direct validation is needed to determine whether the proposed reward mechanism genuinely encourages the model to generate high-quality questions near its capability boundary, rather than merely questions with high answer uncertainty.
-
Section 4.3.1 constructs the Quality Supervisor by reusing the current solver to verify generated questions and pseudo-labels, but this design may introduce correlated errors between the solver and the supervisor. According to Section 4.4.2, pseudo-labels are obtained through majority voting over 10 sampled solver responses, while Equation (13) allows samples with consistency scores between 0.3 and 0.8 to proceed to subsequent verification. This means that some candidate answers may receive support from only 3 sampled responses and still have a chance to enter the training data after passing supervisor verification. When the solver systematically misjudges certain types of visual questions, the same model acting as the supervisor may also approve incorrect answers, allowing erroneous supervision signals to be repeatedly reinforced during subsequent self-evolution. Although Appendix C.1 evaluates the supervisor using Qwen3.5-Plus as an external reference, the average precision is only 0.72 and the recall is 0.885, while this validation still relies on judgments from another model. The paper does not further report independently human-verified accuracy for the final retained pseudo-labels or analyze error accumulation across different skill categories. Therefore, the existing evidence supports the effectiveness of quality filtering to some extent, but is insufficient to demonstrate that this shared-parameter self-verification mechanism can reliably suppress long-term error propagation.
-
The Skill-aware Dynamic Balancing mechanism in Section 4.3.2 primarily computes rewards based on the six skill categories declared by the questioner and their recent generation frequencies, and constructs the training set through approximately uniform sampling. This approach can adjust the number of samples across categories, but a more balanced category distribution does not necessarily imply richer reasoning content in generated questions or more balanced improvements in model capabilities. In particular, the difficulty levels and task formats within each of the six skill categories may vary substantially, and controlling category frequencies alone cannot prevent the generation of many similar questions within the same category. Furthermore, the existing experiments ablate the skill-frequency reward and training-stage stratified sampling together as a single component, without separately analyzing their contributions. Table 2 shows that introducing the complete skill-balancing mechanism improves the average scores by only 0.56, 0.09, and 0.55 percentage points at Steps 20, 40, and 60, respectively, compared with Fine-grained + Sup. Although these results indicate that the mechanism provides some benefits, the paper does not further report actual changes in solving capabilities across different skills, nor does it provide an independent comparison with a simple uniform sampling strategy. Therefore, it remains difficult to determine whether the performance improvements arise from dynamic skill regulation or from more conventional balancing of the training data distribution.
-
Section 4.2 presents Fine-grained Role Alternation as an important design for improving self-evolving efficiency and conducts comparisons under the same number of parameter update steps. However, equal numbers of update steps do not necessarily imply equal computational costs. More frequent switching between the questioner and solver increases the number of question generation, pseudo-label construction, and supervisor verification operations. In fact, Appendix C.8 reports that, under the same backbone model, image collection, and update budget, the complete RISE training process takes 73 hours, compared with 65 hours for the reproduced VisPlay, representing a 12.3% increase. Although RISE improves the average score from 49.96 to 52.26, this does not directly demonstrate an advantage in actual computational efficiency. Furthermore, Appendix C.3 shows that when the alternation cycle is further shortened to , the score at Step 20 reaches 50.94, higher than the 50.64 achieved by the default . However, at Step 60, the score instead decreases to 50.71, below the 51.71 achieved by . This indicates that more frequent alternation does not always lead to better results. The paper should further distinguish parameter-update efficiency from actual training efficiency, clarify the rationale for selecting a particular alternation frequency, and examine whether the performance advantage remains under matched computational costs.
-
Section 5 mainly validates RISE through comparisons with different role alternation strategies and component ablations, but its substantive incremental contribution over existing self-evolving methods remains insufficiently established. The three core components respectively shorten alternation cycles, filter low-quality samples based on model judgments, and adjust the sampling distribution according to category frequencies. These designs are closer to a combination of improvements to existing training procedures. Although Appendix C.9 provides reference comparisons with Vision-Zero, EvoLMM, and MM-Zero, and also reproduces VisPlay, the results for the other methods come from different training settings. The authors also explicitly acknowledge that these cross-paper results cannot support a rigorous ranking of methods. The only controlled reproduction, VisPlay, corresponds to a coarse-grained alternation setting without quality supervision or skill balancing. Therefore, the advantage of the complete model simultaneously includes the benefits of multiple training strategies. The existing ablations demonstrate that these components have individual effects, but comparisons with other simple self-training strategies under matched computational budgets are still lacking, such as using a fixed questioner, applying only quality filtering, or adopting static skill balancing. Consequently, it remains unclear how much of RISE's advantage comes from the proposed dual-role coordination mechanism and how much could be achieved through conventional data filtering and training scheduling. This limits my assessment of the methodological novelty and actual incremental contribution of the work.
-
Section 5.2 describes RISE as achieving stable and sustained self-evolving improvements, but the current experiments provide limited evidence for long-term evolution and cross-model generalization. The main experiments use only two models from the same Qwen-VL family, Qwen2.5-VL-7B and Qwen3-VL-8B, and a single image source, Vision-47K. These settings are insufficient to demonstrate that the method would have similar effects across different model architectures, pretrained capabilities, and image distributions. Appendix C.7 further extends Qwen3-VL-8B training to 100 steps. Although the average score increases from 57.37 at Step 60 to 58.05 at Step 100, the additional 40 training steps yield only a 0.68-percentage-point improvement, while performance on several benchmarks fluctuates or declines. Meanwhile, Appendix C.2 shows that Qwen2.5-VL experiences substantial performance degradation without the supervisor, whereas the stronger Qwen3-VL can still maintain some improvement. This suggests that training stability may depend considerably on the base model's own ability to generate and recognize correct answers. Therefore, the current experiments support the effectiveness of RISE in improving self-evolution within the tested models and training range, but further evidence is needed to establish whether it can reliably sustain improvements over longer training periods and under more diverse model conditions.
Questions for authors
Please refer to Critical Weaknesses.
10 comments
Response to dDK1 (Part 2)
W2: Does the shared-parameter supervisor lead to compounding errors? (Part 1)
A: Thank you for raising the concern about correlated errors arising from parameter sharing. We agree that the supervisor, instantiated from the current solver, is not an independent external judge and therefore cannot completely eliminate self-confirmation errors. For example, the solver and supervisor may overlook the same visual detail or agree on an internally consistent but incorrect answer. We adopt this design to provide effective quality checks on generated samples without deploying an additional supervisor model, rather than to guarantee that every accepted pseudo-label is correct.
Mechanistically, sharing parameters does not mean that generation and verification perform the same task. The solver generates an answer from the image and question; the supervisor additionally receives the candidate answer and uses a separate verification prompt to check whether it is supported by the visual evidence and satisfies the question's requirements. Providing the candidate answer allows the model to check specific inconsistencies, giving it an opportunity to identify errors in its own generated answers. We use this judgment as a filtering signal: candidates that fail verification are rejected, while passing verification is not treated as proof of correctness. Acceptance instead depends jointly on this check, question-validity assessment, and consistency filtering. The lower bound of the consistency window only determines whether a candidate enters subsequent checks; it does not imply that a small number of supporting answers is sufficient to guarantee label reliability.
Furthermore, verification responses are not themselves the GRPO training targets, and the solver receives no direct reward for approving its own answers. Thus, the mechanism does not directly optimize the supervisor's tendency to accept its own outputs. Nevertheless, the shared parameters change as the solver is updated. Once an incorrect pseudo-label passes the checks and enters training, it can indirectly influence generation and verification in the next round. We therefore acknowledge that an indirect feedback path remains, and its actual effect needs to be assessed through quality audits during training. Our existing process statistics do not show a sustained deterioration in overall supervision quality during self-evolution.
Table: Qwen2.5-VL supervisor precision and recall
| Training step | 5 | 10 | 15 | 20 | 25 | 30 | 35 | 40 | 45 | 50 | 55 | 60 | Mean |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Precision | 0.68 | 0.60 | 0.62 | 0.65 | 0.69 | 0.66 | 0.74 | 0.65 | 0.70 | 0.68 | 0.67 | 0.66 | 0.667 |
| Recall | 0.70 | 0.75 | 0.73 | 0.67 | 0.69 | 0.77 | 0.72 | 0.70 | 0.65 | 0.73 | 0.74 | 0.67 | 0.710 |
The external audit in Appendix C.1 and the additional Qwen2.5-VL audit above show fluctuations and differences across backbones in the supervisor's detection capability, but no sustained downward trend.
We also conducted an additional external audit using the stronger Qwen3.8-max. For each backbone, we sampled 600 finally accepted questions from each of six training stages: Steps 0–10, 10–20, 20–30, 30–40, 40–50, and 50–60. We assessed question validity and pseudo-label correctness separately and specifically measured the answer error rate among valid questions. Thus, the denominator in the tables is the number of questions judged valid by the external evaluator within the corresponding stage or skill category. Step denotes the final step of each training stage.
Table: Pseudo-label error rates by training stage
| Backbone | Step 10 | Step 20 | Step 30 | Step 40 | Step 50 | Step 60 |
|---|---|---|---|---|---|---|
| Qwen2.5-VL-7B | 20.43% | 24.37% | 26.08% | 23.95% | 22.20% | 25.22% |
| Qwen3-VL-8B | 18.63% | 17.13% | 17.31% | 17.19% | 17.44% | 19.53% |
These results show that residual errors remain, but no sustained increase is observed across the examined stages, even for the weaker model. The VCR curves in Figure 3 also show that including quality supervision better maintains training-data quality than removing it.
Response to dDK1 (Part 3)
W2: Does the shared-parameter supervisor lead to compounding errors? (Part 2)
A: We further provide the analysis of error accumulation across skills that you requested. As above, these are pseudo-label error rates among valid questions.
Table: Qwen2.5-VL-7B --- pseudo-label error rates by skill
| Skill | Step 10 | Step 20 | Step 30 | Step 40 | Step 50 | Step 60 |
|---|---|---|---|---|---|---|
| Coarse Perception | 15.08% | 3.57% | 10.53% | 15.92% | 13.16% | 5.88% |
| Fine-grained Perception | 18.39% | 25.49% | 29.29% | 30.77% | 27.89% | 24.32% |
| Instance Reasoning | 21.50% | 18.18% | 28.57% | 22.73% | 8.33% | 21.43% |
| Logical Reasoning | 16.98% | 16.67% | 18.18% | 26.32% | 16.67% | 11.11% |
| Math & Counting | 20.83% | 27.55% | 25.77% | 25.00% | 22.99% | 29.63% |
| Science & Technology | 22.37% | 32.73% | 30.51% | 23.81% | 33.33% | 25.00% |
Table: Qwen3-VL-8B --- pseudo-label error rates by skill
| Skill | Step 10 | Step 20 | Step 30 | Step 40 | Step 50 | Step 60 |
|---|---|---|---|---|---|---|
| Coarse Perception | 16.67% | 15.34% | 13.27% | 16.05% | 13.76% | 15.00% |
| Fine-grained Perception | 23.16% | 18.81% | 17.24% | 12.50% | 16.67% | 10.71% |
| Instance Reasoning | 11.65% | 16.04% | 23.53% | 14.04% | 9.09% | 5.00% |
| Logical Reasoning | 7.34% | 13.64% | 15.19% | 6.35% | 10.00% | 17.85% |
| Math & Counting | 16.52% | 16.96% | 10.84% | 13.77% | 23.81% | 23.04% |
| Science & Technology | 38.64% | 20.00% | 26.32% | 28.03% | 17.50% | 20.00% |
These results show fluctuations across stages and skills, but no uniform, sustained increase in error rates during training. Thus, we do not observe the pattern of compounding deterioration you are concerned about.
To assess the reliability of the external evaluations, we additionally performed a manual check. We sampled 50 finally accepted questions across training stages, manually examined question and pseudo-label quality, and checked agreement with the stronger model gpt6astra. Human judgments agreed with Qwen3.5-Plus on 46 questions, yielding 92% agreement, and agreement with gpt6astra was 88%. Disagreements mainly concerned answer granularity rather than clearly invalid questions or unequivocally incorrect answers. This check provides supplementary support for the external evaluations, although its sample size is limited and the results are for reference only.
We also conducted a frozen-supervisor control experiment. The evaluation results for a frozen supervisor and the shared supervisor updated alongside the solver on Qwen2.5-VL are shown below.
| Model / stage | MMMU | MMVet | RealWQA | ChartQA | MathVerse | MathVision | MathVista | AVG |
|---|---|---|---|---|---|---|---|---|
| Base Model | 49.71 | 51.83 | 57.12 | 79.48 | 40.48 | 23.21 | 58.70 | 48.17 |
| Frozen supervisor — Step 20 | 53.56 | 54.59 | 58.04 | 81.20 | 42.63 | 27.18 | 59.80 | 50.61 |
| RISE — Step 20 | 54.03 | 57.80 | 57.52 | 81.68 | 43.65 | 27.36 | 60.40 | 51.20 |
| Frozen supervisor — Step 40 | 54.84 | 57.34 | 59.22 | 82.40 | 43.73 | 28.13 | 60.10 | 51.68 |
| RISE — Step 40 | 54.03 | 56.88 | 58.30 | 81.84 | 44.19 | 28.73 | 60.10 | 51.74 |
| Frozen supervisor — Step 60 | 54.73 | 55.96 | 60.52 | 82.32 | 44.16 | 28.47 | 60.20 | 51.94 |
| RISE — Step 60 | 55.31 | 57.80 | 60.39 | 82.08 | 44.95 | 28.32 | 61.10 | 52.26 |
The two settings yield similar results, and the differences may partly reflect training randomness. The frozen supervisor shows no performance advantage in this comparison. These results complement the audits during training and support the feasibility of reusing the current solver as the supervisor over the tested training range, while avoiding an additional frozen supervisor model copy.
Our method cannot completely eliminate erroneous samples, but the sample-quality analyses and ablation results support its practical contribution: under the same fine-grained alternation setting, adding quality supervision raises Qwen2.5-VL's Step-60 average score from 44.85 to 51.71 and substantially mitigates the degradation of intermediate training-data quality.
Response to dDK1 (Part 1)
Thank you for your careful reading and constructive feedback. We address your questions and concerns point by point below and will incorporate the relevant supplementary results into the revised manuscript.
W1: Whether the difficulty and validity rewards encourage high-quality, learnable questions.
A: Thank you for your detailed analysis of the reward design. First, we would like to clarify that λv=0.2 is the additive coefficient of the validity term; it does not mean that validity accounts for only 20% of the total reward. Its actual influence must be understood in relation to the numerical scales of the other reward terms. During training, we observed that the mean difficulty reward is typically below 0.1 in the early stages and approximately 0.2–0.3 in the later stages as self-evolution stabilizes. In comparison, every question that passes the validity check receives an additional reward of 0.2. The validity term therefore provides a strong preference for quality early in training and remains comparable in magnitude to the difficulty reward later on. It is not a negligible correction relative to the difficulty term.
The motivation for this setting is to promote basic question quality early in training through a strong validity incentive. Once the questioner can satisfy the validity requirements relatively consistently, the difficulty term provides an additional optimization preference, encouraging it to explore valid questions that are more challenging for the current solver. We agree that an additive reward does not impose a strict priority for validity, so some invalid questions may still receive higher rewards than simple valid questions, although such cases represent a small proportion. Our goal is to reduce the tendency to generate low-quality questions and their proportion in the training data, rather than to claim that this soft constraint eliminates every instance of misaligned incentives. During data construction, candidates must also pass both validity and pseudo-label correctness checks before being used for solver training.
Regarding the more direct validation you requested, the valid-and-correct rate (VCR) in Figure 3 is specifically designed to assess whether questions meet quality requirements while retaining uncertainty for the solver. Here, valid requires a clear question, consistency between its task type and content, relevance to the image, and an answer that depends on sufficient information provided in the image; correct requires the pseudo-label used for training to be the correct answer. These properties are assessed by a strong external model that is not involved in training. Thus, VCR goes beyond measuring disagreement among the solver's answers to examine the quality of both the questions and their supervision targets. We regard samples that pass the [0.3, 0.8] consistency window and satisfy both valid and correct as learnable candidates that pose a moderate challenge to the current model. Figure 3 shows that removing quality supervision causes the proportion of high-quality samples to decline substantially during training, falling below 10% in the later stages for Qwen2.5-VL. With quality supervision, this proportion remains at a higher level. Downstream results are consistent with this change: under the same fine-grained alternation setting, with skill balancing disabled in both cases, adding quality supervision improves the Step-60 average score from 44.85 to 51.71. Together, these results support the contribution of the full quality-control mechanism in terms of both sample quality and learning outcomes.