- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper studies how metric depth supervision can improve spatial reasoning in VLMs. The authors combine joint depth-and-reasoning SFT with D-GRPO, which weights task rewards using a reasoning-quality score. They also introduce WorldDepthBench to test depth-dependent judgments under physical constraints. The contribution lies both in the training recipe and benchmark.
Critical strengths
The motivation is clear, and WorldDepthBench covers useful physical constraints. RL improves accuracy by 6.85 points over SFT while largely preserving average depth accuracy.
Critical weaknesses
-
Comparisons with related spatial reasoning RL methods are missing. The paper should include methods that use geometry-aware rewards or model-based feedback to improve spatial reasoning. These comparisons would help clarify the benefit of D-GRPO.
-
The quality-gate ablation is incomplete. The current experiments do not isolate its contribution. A comparison with task-reward-only GRPO, is needed.
-
The method is validated on only one 2B backbone. Its effectiveness across model families and scales remains unclear. Testing another backbone or a larger model would help establish whether the gains extend beyond the current setting.
Questions for authors
-
Why use the external VLM to score responses instead of distilling its reasoning traces?
-
What alternative reward designs did you consider?
7 comments
Official Response to Reviewer 62C4 (Part 2/4)
D-GRPO achieves the highest accuracy across all four WorldDepthBench categories and the highest mean δ1. Its overall accuracy exceeds DepthLM-style GRPO, GRPO + SNRA, and the Embodied-R reward adaptation by 7.97, 5.68, and 5.26 percentage points, respectively.
The differences are particularly pronounced in action decisions, where D-GRPO reaches 34.06%, compared with 23.65–26.56% for the alternative reward designs. D-GRPO also preserves the SFT checkpoint’s metric perception, with mean δ1 increasing from 0.914 to 0.915, whereas the alternatives reach 0.904–0.905. Thus, its reasoning gains are accompanied by maintained depth accuracy.
These results support the combined design of D-GRPO: verifiable rewards supervise metric accuracy, depth ordering, and decisions under physical constraints, while the thinking-quality gate assesses how the response connects visual evidence and depth estimates to its conclusion. The component ablations in our response to W2 further isolate the contributions of these rewards and the gate.
We will include these comparisons, the shared experimental settings, and the details of each reward adaptation in the revision.
References
[1] Zhipeng Cai et al. DepthLM: Metric Depth from Vision Language Models. arXiv:2509.25413, 2025.
[2] Siwen Jiao et al. Smooth Operator: Smooth Verifiable Reward Activates Spatial Reasoning Ability of Vision-Language Model. EMNLP 2026; arXiv:2601.07695.
[3] Baining Zhao et al. Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning. arXiv:2504.12680, 2025.
W2. About the Thinking-Quality Gate Ablation
The quality-gate ablation is incomplete. The current experiments do not isolate its contribution. A comparison with task-reward-only GRPO, is needed.
Thank you for the suggestion. We have completed a matched comparison between full D-GRPO and task-reward-only GRPO, together with ablations of the individual reward components. All RL variants start from the same SFT checkpoint and use the same training data, sampling settings, and training budget. In the task-reward-only variant, we remove the thinking-quality gate while retaining all verifiable task rewards, directly isolating the gate’s contribution.
The results are summarized below. WorldDepthBench scores are accuracy (%), and mean δ1 is averaged across the seven depth-evaluation datasets.
| Variant | WDB overall | Perc. | Geo. | Act. | Gen. | Mean δ1 |
|---|---|---|---|---|---|---|
| SFT | 38.93 | 51.98 | 35.42 | 25.94 | 45.83 | 0.914 |
| D-GRPO (full) | 45.77 | 57.19 | 41.77 | 34.06 | 54.37 | 0.915 |
| w/o thinking-quality gate (task-reward-only GRPO) | 39.49 | 50.42 | 36.56 | 27.19 | 48.13 | 0.906 |
| w/o ranking reward | 42.08 | 53.13 | 41.46 | 26.67 | 52.08 | 0.909 |
| w/o metric reward | 37.29 | 51.04 | 33.85 | 20.21 | 50.83 | 0.901 |
| w/o multiple-choice reasoning reward | 39.64 | 53.23 | 37.19 | 21.88 | 52.92 | 0.903 |
Full D-GRPO exceeds task-reward-only GRPO by 6.28 percentage points in overall accuracy, with improvements across all four categories. It also maintains the SFT checkpoint’s metric-depth accuracy (mean δ1: 0.914 → 0.915), whereas removing the gate lowers mean δ1 to 0.906. This matched comparison supports the gate’s contribution to spatial reasoning performance while preserving metric perception.
The remaining ablations show that each reward component also contributes to the full model’s performance. Removing the metric or ranking reward lowers both overall accuracy and mean δ1. Removing the multiple-choice reasoning reward reduces action-decision accuracy from 34.06% to 21.88%, supporting the importance of explicitly rewarding decisions under physical constraints.
We will include these completed ablations and their shared experimental settings in the revision.
Official Response to Reviewer 62C4 (Part 3/4)
W3. About the Effect of Model Scale
The method is validated on only one 2B backbone. Its effectiveness across model families and scales remains unclear. Testing another backbone or a larger model would help establish whether the gains extend beyond the current setting.
Thank you for the suggestion. We have extended our framework to Qwen3-VL-8B-Thinking to test whether its benefits extend to a larger backbone. We examine metric-depth perception after SFT and spatial reasoning after D-GRPO separately.
(a) Metric-depth perception after SFT.
Using the same depth-supervision data, increasing the backbone from 2B to 8B improves mean δ1 from 91.4% to 91.7% across the seven evaluation datasets:
| Backbone | Mean δ1 after depth-supervised SFT (%) |
|---|---|
| Qwen3-VL-2B-Thinking | 91.4 |
| Qwen3-VL-8B-Thinking | 91.7 |
This modest 0.3-percentage-point gain suggests that the 2B backbone already provides sufficient capacity for accurate metric-depth estimation under our training setup.
(b) Spatial reasoning after D-GRPO.
Following D-GRPO, DepthThinker-8B-RL outperforms both DepthThinker-2B-RL and DepthThinker-8B-SFT across all four WorldDepthBench categories:
| Model | WDB overall | Perc. | Geo. | Act. | Gen. |
|---|---|---|---|---|---|
| DepthThinker-2B-RL | 45.77 | 57.19 | 41.77 | 34.06 | 54.37 |
| DepthThinker-8B-SFT | 46.93 | 52.81 | 44.27 | 35.94 | 62.50 |
| DepthThinker-8B-RL | 49.79 | 60.21 | 45.10 | 37.08 | 63.75 |
Compared with DepthThinker-2B-RL, the 8B model improves overall accuracy by 4.02 percentage points, including gains of 3.33 percentage points in geometric reasoning and 3.02 percentage points in action decisions. D-GRPO also raises the 8B model’s overall accuracy from 46.93% to 49.79%, a gain of 2.86 percentage points over its SFT counterpart, with improvements across all four categories. Relative to the original Qwen3-VL-8B-Thinking baseline (42.47%), DepthThinker-8B-RL achieves an overall gain of 7.32 percentage points, further supporting the effectiveness of our framework at the larger scale.
These results suggest that additional model capacity helps translate depth estimates into stronger spatial reasoning and action decisions under physical constraints. They support the applicability of our framework at both the 2B and 8B scales within the Qwen3-VL family, while evaluation across other model families remains a direction for future work. We will include these 8B results and the corresponding analysis in the revision.
Official Response to Reviewer 62C4 (Part 1/4)
We thank the reviewer for the clear summary and for acknowledging the motivation of WorldDepthBench and the RL gains. Our responses follow.
W1/Q2. About Related Spatial-Reasoning RL Methods and Alternative Rewards
Thank you for the suggestion. We have added comparisons with three alternative reward designs covering numerical depth supervision, smooth numerical rewards, and model-based reasoning feedback:
DepthLM-style GRPO. Following one of the numerical reward formulations evaluated in DepthLM [1], we compute negative absolute relative error for numerical tasks:
=-\frac{1}{N}\sum_{i=1}^{N}\frac{|\hat d_i-d_i|}{d_i}.$$ To make this reward compatible with multiplicative quality gating, we apply a fixed bounded transformation: $$\widetilde R_{\mathrm{AbsRel}} =\frac{1}{1-R_{\mathrm{AbsRel}}} =\frac{1}{1+\frac{1}{N}\sum_{i=1}^{N}\frac{|\hat d_i-d_i|}{d_i}}.$$ The transformed reward lies in $(0,1]$, equals 1 for an exact prediction, and decreases smoothly as the prediction error increases. We then compute the final numerical-task reward as $$R_{\mathrm{final}}^{\mathrm{AbsRel}} =G\cdot\widetilde R_{\mathrm{AbsRel}}.$$ This bounded transformation is our task-specific adaptation of the negative AbsRel reward. It preserves the ordering of numerical prediction accuracy while ensuring that, for a fixed prediction error, higher reasoning quality yields a higher final reward. We have also retained the ranking rewards for multi-point missions, as well as MCQ rewards.GRPO + SNRA. We adopt the Smooth Numerical Reward Activation (SNRA) operator from Smooth Operator [2] within our standard GRPO implementation. SNRA maps numerical prediction errors to dense rewards through a parameterized sigmoid:
=\frac{1}{N}\sum_{i=1}^{N}\frac{2}{1+\exp(k(t)e_i)}, \qquad e_i=\left(\frac{\hat d_i-d_i}{d_i+10^{-8}}\right)^2.$$ We use a predefined linear schedule, $$k(t)=2+18\frac{t-1}{159}, \qquad t\in\{1,\ldots,160\},$$ where $t$ is the actual training update index. This schedule increases the sigmoid sharpness from 2 at update 1 to 20 at update 160. Since the SNRA reward already lies in $[0,1]$, no additional range transformation is required. We apply the same reasoning-quality gate $G$ to obtain the gated numerical reward: $$R_{\mathrm{gated}}^{\mathrm{SNRA}}(t) =G\cdot R_{\mathrm{SNRA}}(t).$$ The original ranking rewards for multi-point tasks and the MCQ rewards remain unchanged.Embodied-R-style reward adaptation. Inspired by the answer re-derivation feedback in Embodied-R [3], we use a frozen reference model to assess consistency between the reasoning and final answer. We retain our original metric, ranking, and MCQ task rewards and replace the quality gate with an additive reward:
=R_{\mathrm{task}}+0.1I_{\mathrm{valid}}+0.25C,$$ where $I_{\mathrm{valid}}$ indicates that the response passes completion, format, and numerical/schema checks. Reference feedback is applied only to valid responses with non-empty reasoning and a correct original answer. A frozen copy of the initial SFT model re-derives an answer from the public question, reasoning text, and required answer format. It receives no image, hidden ground truth, or separate original final-answer field; values or conclusions already present in the reasoning text remain unchanged. The reference runs at temperature 0 with a 1,024-token limit, and its answer is checked locally. We set $C=1$ if the reference produces a correct MCQ answer or if every numerical prediction satisfies $$\max\!\left(\frac{\hat d_i}{d_i},\frac{d_i}{\hat d_i}\right)<1.25;$$ otherwise, $C=0$. The same correctness criterion determines whether the original response is eligible for reference feedback. Thus, numerical consistency requires both the original and re-derived answers to satisfy the same tolerance, rather than exact equality between their predicted values.Results are reported below, with WorldDepthBench accuracy in percentages and mean δ1 averaged across the seven depth-evaluation datasets.