- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
In this work, the authors propose an active visual reasoning framework based on reinforcement learning. The methodology contains three parts: 1) Spatially indexed evidence refinement, where evidence is computed for each cell and can be refined using embeddings at increased resolutions. 2) Answer-support utility, which determines whether intermediate steps are useful based on answer correctness. 3) Utility-aware GRPO, where utility is included as part of the reward. Experiments on multiple benchmarks demonstrate the effectiveness of the proposed method compared with vanilla GRPO on Qwen2.5-VL models.
Critical strengths
- The problem is well-motivated and the proposed method is intuitive. REFINE separate the storage decision from the acquisition decision, which is a interesting and useful conceptual contribution.
- Experiments cover different model size and benchmarks, as well as comprehensive ablation, demonstrate the effectiveness of proposed method.
Critical weaknesses
-
The presentation of the paper need major improvement. It's hard to follow and understand when reading first time. For example, Figure 1 is difficult to read without legend and some terms are used before define them, e.g. "cell" in L162.
-
There are mismatches between the numbers reported in Table 1 and Figure 5. For example, Qwen2.5-VL-7B achieves >76 on V* in Figure 5, while 70.68 is reported in Table 1.
-
The baselines numbers are significantly lower than the ones reported in the original paper, which makes the conclusion not convincing. For example, Deepeyes reports 90.1 on V* while the Table 1 it's 84.21. Additionally, for zero-shot Qwen2.5-VL-7B, ACTIVE-o3 [1] reports 67.9 while the paper reports 60.6.
-
Comparisons, citation and discussion with similar RL-based methods are missing, e.g. Adaptive-CoF [2] and Mini-o3 [3], which target at the same problem setting and report better results on some benchmarks like V* than REFINE.
-
There is no explanation about the training data. It's hard to tell whether the improvement comes from model learns to actively reasoning over visual cues or in-domain training data brings the performance gain.
-
The experiments are solely based on Qwen2.5-VL, which is kind of outdated. Does the proposed method generalize to latest MLLMs like Qwen3VL / Qwen3.5?
[1] Zhu, M., Zhong, H., Zhao, C., Du, Z., Liu, M., Huang, Z., Li, A., Chen, H., Zou, C., Chen, J. and Yang, M., 2025. ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning. arXiv preprint arXiv:2505.21457.
[2] Zhang, X., Gao, Z., Zhang, B., Li, P., Zhang, X., Liu, Y., Yuan, T., Wu, Y., Jia, Y., Zhu, S.C. and Li, Q., 2025. Adaptive chain-of-focus reasoning via dynamic visual search and zooming for efficient vlms. arXiv preprint arXiv:2505.15436.
[3] Lai, X., Li, J., Li, W., Liu, T., Li, T. and Zhao, H., 2026, April. Mini-o3: Scaling up reasoning patterns and interaction turns for visual search. In International Conference on Learning Representations (Vol. 2026, pp. 76722-76746).
Questions for authors
-
What is the "consistency reward" in Figure 3? Was it part of the training reward in Eq (5)?
-
Is Figure 5 produced from REFINE's own training and evaluation runs?
-
Why are the reported metrics so far below the published numbers?
-
What training data was used, such as source, size, task mix?