- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Hierarchical Volumetric Reasoning for aerial vision-language navigation. The method first lifts RGB-D observations into a Multi-Scale Voxel Map that represents geometric and semantic information at coarse-to-fine resolutions. It then uses instruction-conditioned decision and proxy tokens to retrieve relevant voxel features, while attention scores route reasoning toward selected regions at finer scales. The final decision token is combined with a recurrent state to predict navigation actions. Experiments on AerialVLN-s show improvements over learning-based baselines and competitive performance relative to LLM-based methods, together with a reported inference latency of 0.09 seconds per step.
Critical strengths
- A clear and efficient way to bring 3D structure into aerial VLN. Most aerial agents reason over 2D views, grid maps or topological graphs. This paper lifts each observation into a coarse-to-fine voxel volume and lets the instruction decide which regions to refine. The design makes sense for UAVs, where relevant cues appear at very different heights and scales. It also stays cheap: 0.09 s and 1.71 GB per step, compared with seconds and tens of GB for LLM-based agents. Among learning-based agents, the gain on val seen is large.
- The evaluation is more careful than usual for this benchmark. Main results are averaged over five runs with standard deviations. The ablations cover the representation, the reasoning levels, the voxel selection ratio and the routing budget, and they show that routing is what keeps the finer levels within memory. The paper also measures occupancy quality next to navigation performance, which helps connect the quality of the 3D representation to downstream decisions.
Critical weaknesses
- It is unclear where the improvement comes from. Most of the gain in the ablation comes from adding MSVM, and the instruction-driven reasoning on top adds a smaller amount. No baseline receives the same depth input and auxiliary supervision without the volumetric structure, and the starting baseline is weaker than existing learning-based agents. It is hard to tell whether the gain comes from the voxel representation or simply from the extra depth input and occupancy labels.
- The claims go beyond what the representation and evaluation support. The volume is rebuilt from a single frame at every step, covers a limited range around the agent, and carries no information across steps. It is closer to a 3D view of the current observation than to a scene map, so the claim of reasoning from global scene layout is overstated. The evaluation is also limited. Only AerialVLN-s is used. The comparison with LLM-based agents is up to date, but the most recent learning-based baseline is LAG from 2023, even though the agent is itself learning-based. This makes it hard to tell how much of the gain over learning-based methods would remain against recent non-LLM aerial agents.
Questions for authors
- Is at test time the ground-truth simulator depth, and are the extrinsics in Eq. (2) ground-truth poses? Do LAG, Seq2Seq and CMA in Table 1 receive the same depth input?
- How does the agent perform with MSVM trained without occupancy supervision, and with a 2D or BEV representation that receives the same depth input and occupancy losses? This would show whether the gain comes from volumetric reasoning or from the extra input and supervision.
- HVR is trained only through , and TopK in Eq. (6) is non-differentiable. How does a parent voxel that should have been selected but was not receive a learning signal? How often does the routed region at the middle and fine levels contain the next expert waypoint or the goal, and how does this routing compare with occupancy-based or random routing under the same budget?
- The volume covers only [−8 m, 8 m] vertically and 51.2 m forward. How does the agent handle steps where the next landmark or the goal lies outside this range?
- The volume is rebuilt from the current frame at every step. Once a landmark leaves the field of view, is the GRU state the only memory that carries it? Did you try fusing voxels across steps using poses?
- The most recent learning-based baseline in Table 1 is LAG (2023). Can you compare with at least one recent non-LLM aerial agent under the same protocol?
7 comments
Responses to Reviewer 7fGi (2/5)
W2-2: "The evaluation is also limited. Only AerialVLN-s is used"
A2-2: Thanks for your comment. We evaluate our agent on OpenFly [1]. We retrain our agent using its official training split, using the same architecture, two-stage training recipe, and other key hyperparameters (e.g., volume resolution, perception range, number of selected voxels in HVR, etc.). As shown in the table below, our agent outperforms all baselines on test seen split (e.g., +14.5% SR over NaVila, +0.5% SR over OpenFly-Agent). On test unseen split, our agent remains competitive, achieving 20.7% SR and 17.2% SPL. The results demonstrate the proposed method remains effective across benchmarks.
| Agent | LLM | Test-Seen NE | Test-Seen SR | Test-Seen OSR | Test-Seen SPL | Test-Unseen NE | Test-Unseen SR | Test-Unseen OSR | Test-Unseen SPL |
|---|---|---|---|---|---|---|---|---|---|
| Seq2Seq | -- | 205 | 2.9 | 24.3 | 2.6 | 229 | 2.1 | 20.6 | 1.1 |
| CMA | -- | 161 | 5.4 | 28.1 | 4.8 | 217 | 4.6 | 24.4 | 2.1 |
| AerialVLN | -- | 139 | 7.5 | 30.0 | 6.8 | 214 | 7.3 | 28.1 | 4.4 |
| NaVid | 153 | 13.0 | 38.2 | 11.6 | 210 | 10.8 | 27.2 | 5.0 | |
| NaVila | 132 | 20.3 | 53.5 | 17.8 | 202 | 14.7 | 42.1 | 9.6 | |
| OpenFly-Agent | 93 | 34.3 | 64.3 | 24.9 | 154 | 22.6 | 56.2 | 19.1 | |
| Ours | -- | 94 | 34.8 | 67.1 | 25.0 | 164 | 20.7 | 56.8 | 17.2 |
We have added this quantitative comparison on OpenFly in the revised version (Appendix B.5, Table 11, L954-977).
[1] OpenFly: A Comprehensive Platform for Aerial Vision-Language Navigation. ICLR 2026.
Responses to Reviewer 7fGi (3/5)
W2-3: "but the most recent learning-based baseline is LAG from 2023, even though the agent is itself learning-based. "
A2-3: Thank you for highlighting this gap in our baseline coverage. With the flourishing of LLM/MLLM, most recent aerial agents developed on AerialVLN-s are LLM/MLLM-based. To address this, we adapt two recent learning-based, non-LLM-based aerial agents MGP (ICCV 2025) [1], HETT (AAAI 2026) [2] to the AerialVLN-s setting using the same training and evaluation protocol.
The results are shown in the table below, our agent achieves consistent performance gains, e.g., on val seen +5.1% SR / +6.1% SDTW over MGP, +3.9% SR / +5.3% SDTW over HETT; on val unseen +3.6% SR / +2.8% SDTW over MGP, +3.0% SR / +2.3% SDTW over HETT.
| Agent | Pano. | Depth | LLM | NE (val seen) | SR (val seen) | OSR (val seen) | SDTW (val seen) | NE (val unseen) | SR (val unseen) | OSR (val unseen) | SDTW (val unseen) |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MGP [1] | -- | -- | 95.1 | 11.1 | 24.9 | 6.4 | 130.1 | 5.2 | 14.8 | 1.1 | |
| HETT [2] | -- | -- | 93.2 | 12.3 | 28.5 | 7.2 | 127.0 | 5.8 | 16.2 | 1.6 | |
| Ours | -- | -- | 84.1 | 16.2 | 35.4 | 12.5 | 109.4 | 8.8 | 26.5 | 3.9 |
In the revised version, we incorporate MGP [1] and HETT [2] into Table 1, update the experiment section (Secs. 4.1, 4.2).
[1] CityNav: A large-scale dataset for real-world aerial navigation. ICCV 2025.
[2] History-Enhanced Two-Stage Transformer for Aerial Vision-and-Language Navigation. AAAI 2026.
Q1: "is at test time the ground-truth depth ... are extrinsics ground-truth poses? Do LAG, ... receive the same depth input?"
A1: i) Yes, both and camera poses are ground-truth from simulator. ii) Yes, the baseline models LAG, Seq2Seq and CMA all receive the same ground-truth depth as in the official implementations.
In the revised version, we clarify the source of depth map and camera pose (Sec. 3.5, L292-293), and update Table 1 by adding a depth column.
Q2: "How does the agent perform with MSVM trained without occupancy supervision, and with a 2D or BEV representation that receives the same depth input and occupancy losses?"
A2: Please see W1-2.
Q3-1: "HVR is trained only through , and TopK in Eq. (6) is non-differentiable. How does a parent voxel that should have been selected but was not receive a learning signal? "
A3-1: Thanks for your comments. Recall that HVR employs a multi-layer transformer (MLT, with parameters ) to perform cross-modal reasoning between an instruction-conditioned learnable decision token (along with proxy tokens ), and multi-scale (candidate) voxel features. Before Top-K selection, all current-scale candidate voxels participate in attention aggregation (Eq. 5). The updated tokens are passed to subsequent scales and ultimately used for action prediction. Consequently, optimizes , including the attention projections, to aggregate voxel evidence useful for navigation. Spatial routing (Top-k) reuses these task-trained attention scores to select parent regions for finer-scale reasoning.
Responses to Reviewer 7fGi (1/5)
We sincerely thank Reviewer 7fGi for the constructive feedback. We provide point-to-point responses below, and all corresponding revisions have been incorporated into the revised paper and highlighted in red. All references (e.g., Lines, Tables, Sections) correspond to the updated version.
W1-1: "...and the instruction-driven reasoning on top adds a smaller amount."
A1-1: Thanks for your thoughtful comments. We would like to clarify that the two modules play different roles: MSVM builds the multi-scale representation that encodes evidence across scales, while HVR performs cross-modal reasoning at the appropriate granularity. The +1.3% from HVR is obtained on top of an already strong MSVM baseline (SR 7.5%), and our ablation in Table 4 shows that reasoning over single-scale inputs is substantially worse, indicating that HVR is not a marginal add-on but the mechanism that makes multi-scale evidence usable.
W1-2: "No baseline receives the same depth input and auxiliary supervision ... the starting baseline is weaker. It is hard to tell whether the gain comes from the voxel representation or simply from the extra depth input and occupancy labels. "
A1-2: We appreciate your careful review. We address your concern by adding two new models: i) 2D w/ pretrain: 2D baseline model which is pretrained under the same depth and semantic supervision, and ii) 3D w/o pretrain: MSVM is optimized end-to-end through navigation training. As shown in table below, two observations can be drawn:
i) Volumetric representation is superior. Without geometry and semantic supervision, volumetric representation outperforms 2D representation (2.7% -> 6.5% in SR, 0.8% -> 2.4% in SDTW). With such supervision, volumetric representation improves SR from 4.1% -> 7.5%, and SDTW from 1.2% -> 3.1%. Both demonstrate the effectiveness of multi-scale voxel map.
ii) Auxiliary supervision further helps. Under the same representation, adding geometry and semantic supervision is itself beneficial: it improves the 2D model from 2.7% -> 4.1% in SR, 0.8% -> 1.2% in SDTW, and the 3D model from 6.5% -> 7.5% in SR, 2.4% -> 3.1% in SDTW. The supervision effect is thus consistently positive but smaller than the representation effect in both settings.
Taken together, of the total SR gain from 2.7% to 7.5% (+4.8%), roughly +1.4% is attributable to supervision and +3.4% to the volumetric representation, confirming that the two factors are both beneficial and that the voxel representation is the primary source of the improvement.
Finally, we recognize the original weak 2D baseline (2D w/o pretrain, Table 3 row 1) and its potential unfairness due to the unmatched supervision between our proposed method. In the revised version, we include 2D w/ pretrain as the matched counterpart under identical supervision, so that the representation effect is assessed fairly (Table 3).
W2-1: "... so the claim of reasoning from global scene layout is overstated."
A2-1: We apologize for this confusion. Our intended meaning was that coarse-scale reasoning captures the overall spatial structure within this observed volume (L216-217), before finer-scale reasoning focuses on selected regions. This does not imply access to a complete scene map.
In the revised version, we replace "global scene layout" with "coarse spatial layout" to avoid any ambiguity.