- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies automatic furniture layout generation from architectural floor plans, introducing the AntPlan dataset and the Architect-Ant framework. The method combines SFT, rule-rewarded GRPO, and candidate selection to generate editable coordinate-based layouts for 3D scene construction, evaluated on geometric validity, functional completeness, and visual preference.
Critical strengths
AntPlan provides linked structural, room, and object annotations across 92 classes on real professional floor plans, offering a valuable resource for studying spatial configurations. Architect-Ant uses a coordinate-based DSL with object categories, positions, and dimensions, enabling direct geometric checks, object-level edits, and 3D asset matching.
Critical weaknesses
Table 3 compares methods under inconsistent room subsets (90 vs. 109), task settings (mapping dining rooms to kitchens vs. retaining them), and geometric inputs. Moreover, Architect-Ant selects from 20 candidates using retrieved inventories, while regenerated baselines use 4 candidates. This conflates gains from model training with those from retrieval, candidate selection, and baseline adaptation. In Table 5, moving from SFT to reasoning-enabled GRPO changes both the training stage and output format without a direct-DSL GRPO baseline in the main table, failing to isolate the contributions of RL versus explicit reasoning. Combining SFT with rule-based GRPO closely resembles existing layout post-training methods (e.g., ReSpace). The main text lacks sufficient discussion and comparison to clarify Architect-Ant's specific technical innovations in training strategy or reward design.
Questions for authors
Can you provide a controlled comparison in Table 3 with shared rooms, unified dining/kitchen settings, comparable geometric inputs, and matched inventories and candidate budgets to isolate the effect of model training? Can you include direct-DSL SFT + GRPO in Table 5 under a matched token budget, reporting success rates, scores including all-failed rooms, and paired confidence intervals? Do these results still favor reasoning-enabled GRPO? What are the main technical distinctions of Architect-Ant in training, representation, and reward design compared to prior RL/preference-based layout methods? Can you clarify these via direct comparisons or ablations?
7 comments
Q3. Distinctions from ReSpace and prior RL/preference-based layout methods.
Our contribution relative to ReSpace is RL on the functional quality of the whole room. ReSpace rewards each added object for geometric validity and request match; our reward scores how the objects of the finished room work together (work zones, seating, clearance at doors and windows), so functional coordination becomes an explicit training objective. The reward ablations below show that this functional part drives the gain over SFT; they isolate the reward, not whole-room versus object-by-object generation.
We now cite ReSpace (Bucher & Armeni, 2025) and discuss it in Related Work. Shared ideas: an LLM fine-tuned on a structured scene representation, SFT followed by verifiable-reward post-training, decoupled asset retrieval, and object-level editing.
| ReSpace | Architect-Ant | |
|---|---|---|
| Unit of generation | One object per call; full scenes by sequential addition from an LLM-planned list | The whole room in one response, so relations between objects are optimised jointly |
| Room input | Floor/ceiling polygon; no doors or windows | Walls, doors, windows and railings in metres, plus a furniture request |
| Supported room types | Bedrooms and living/dining rooms (3D-FRONT categories) | Bedrooms, bathrooms, kitchens, living rooms and dining rooms |
| Reward | Binary pass/fail per object (voxel violation, prompt and size match); the final model uses rejection-sampling fine-tuning | Graded whole-room score over 33 rule types, including opening clearance, work zones, seating and wall anchoring |
| Representation | 3D boxes with rotation and text descriptions (richer) | 2D axis-aligned footprints (compact; yaw inferred downstream) |
| Time per scene (Table 3b) | ≈ 760 s | 32 s |
Ablations of the reward design. To isolate the reward, we retrain the same model with different rewards and change nothing else. All ablation arms use the direct-DSL GRPO variant: the unified recipe without the reasoning block, which keeps outputs short and the comparison cheap. Kitchen and living room; the held-out evaluation always uses the full score.
- Binary (our adaptation of ReSpace's pass/fail reward): no grading: +1 if the layout passes all hard geometric and request rules, 0 if it breaks any, −1 if it cannot be parsed; room-specific rules are not used.
- Geometry-only: our graded score (points per violation), with the room-specific rules removed; geometric and request rules are kept.
| Direct-DSL GRPO, reward used | Kitchen mean | Δ vs SFT | Living-room mean | Δ vs SFT |
|---|---|---|---|---|
| none (SFT start) | −0.85 | – | 5.70 | – |
| full graded, room-aware (ours) | 0.25 | +1.10 [+0.24, +2.00] | 6.54 | +0.84 [+0.34, +1.39] |
| binary pass/fail (ReSpace-inspired adaptation) | −0.08 | +0.77 [−0.16, +1.69] | 6.08 | +0.38 [−0.10, +0.86] |
| geometry only | −0.73 | +0.12 [−1.01, +1.23] | 6.23 | +0.53 [+0.14, +0.94] |
The full graded, room-aware reward improves over SFT in both tested room types, with 95% confidence intervals excluding zero. In kitchens, removing the room-specific rules reduces LRS by 0.98 [0.28, 1.75], while functional violations rise from 4.4 to 5.5 penalty points per room. This supports the contribution of room-specific functional rules.
We also evaluated the released ReSpace model in Table 3b on the 90 bedroom/living/dining shells as its full native pipeline (own planner and shipped search).
Q1. A controlled comparison for Table 3.
We understand the concern that differences in inventories, candidate budgets and inputs prevent attributing the original Table 3 gains to model training. We added a comparison that matches these factors across the regenerated methods, alongside a separate comparison using each trained method's native inputs:
- Table 3a, matched comparison against SceneSmith (all 109 shells). SceneSmith cannot take a furniture request, and re-running it is impractical (its Table 18: $13.98 and 3 h 26 min per scene on average). Its authors released one selected scene per benchmark shell, which we use as its entry, without resampling or our selection. We give every other method SceneSmith's own furniture list for that shell: the objects of the released scene mapped to our categories, with SceneSmith's sizes. Architect-Ant, LayoutGPT, Holodeck and LayoutVLM then receive the same shell, the same list, the same 4 seeded runs, the same selection rule and the same scorer. The three baselines use the same Gemma-4-31B backbone without our training, with no solver (LayoutGPT), a constraint solver (Holodeck) or a differentiable optimiser (LayoutVLM). Every shell keeps its SceneSmith room type (31 bedrooms, 32 living rooms, 27 dining rooms, 13 kitchens, 6 bathrooms).
- Table 3b, comparison with the other trained methods on the same SceneSmith shells, restricted to the 90 that all of them can furnish (31 bedrooms, 32 living rooms, 27 dining rooms; the 3D-FRONT methods and ReSpace cannot furnish kitchens or bathrooms). Each method gets its native inputs: Architect-Ant the SceneSmith shell with its doors and windows and a furniture list retrieved from a similar training room; ReSpace (published weights, full native pipeline) the floor shape and a text prompt, its own planner choosing the furniture; ATISS the room shape as a mask; InstructScene a text caption and DiffuScene no input (unconditional), both placed at the centre of the shell. The 3D-FRONT methods and ReSpace choose their own furniture and do not see doors or windows, so this table compares methods as they are used.
Table 3a (SceneSmith's furniture lists, all 109 shells; Architect-Ant, LayoutGPT, Holodeck and LayoutVLM: same shell, list and budget of 4 runs with one selection rule; SceneSmith: its single released scene per shell, not resampled or reselected)
| Method | Base model | Scenes | Valid | # Obj./room | # Obj./10 m² | Cov. % | COL+ % ↓ | OOB % ↓ | Acc. pairs % ↑ | FUN+ % ↑ | LRS ↑ | Time s ↓ | Req. missing % ↓ | Door blk % ↓ (raw) | Win blk % ↓ (raw) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Architect-Ant | Gemma-4 | 109 | 109 | 7.7 | 3.78 | 21.8 | 0.9 | 0.1 | 100.0 | 90 | 9.67 | 29 | 0.0 | 8.8 (10.5) | 1.9 (6.6) |
| LayoutGPT | Gemma-4 | 109 | 109 | 7.4 | 3.67 | 20.8 | 3.8 | 2.7 | 98.7 | 86 | 7.51 | 77 | 3.1 | 28.9 (30.7) | 14.0 (15.9) |
| Holodeck | Gemma-4 | 109 | 109 | 9.6 | 4.67 | 30.6 | 0.0 | 0.0 | 99.5 | 91 | 9.45 | 513 | 23.3 | 0.0 (0.0) | 32.6 (48.4) |
| LayoutVLM | Gemma-4 | 109 | 109 | 7.6 | 3.78 | 22.1 | 0.2 | 6.9 | 97.9 | 89 | 8.81 | 904 | 0.0 | 16.7 (23.7) | 5.8 (13.6) |
| SceneSmith | GPT-5.2 | 109 | 109 | 8.9 | 4.50 | 23.4 | 4.0 | 1.3 | 99.4 | 91 | 8.33 | 1555 | – | 21.1 (22.8) | 1.6 (2.3) |
Architect-Ant has the highest LRS: +1.34 [+0.99, +1.72] over SceneSmith's released scenes, +0.21 [+0.02, +0.41] over Holodeck, +0.86 [+0.64, +1.09] over LayoutVLM and +2.16 [+1.79, +2.54] over LayoutGPT. SceneSmith's own scenes contain some decoration beyond the requested list (e.g. laundry hampers, bath stools, towel ladders, bath mats), which our categories do not cover; it stays in SceneSmith's scored scene, which partly explains its higher object count. Architect-Ant and LayoutVLM place every requested object (0 of 832 missing). LayoutGPT misses 26 (3.1%; mostly rugs 14, beds 3, sofas 3). Holodeck misses 194 (23.3%; chairs 51, rugs 38, floor lamps 23, lamps 17, tables 12), because its LLM object selection treats the list as guidance and substitutes part of it (it adds, e.g., cabinets and side tables). Architect-Ant also leaves windows clear (1.9% blocked vs 32.6% for Holodeck). With the door boxes, Holodeck's solver keeps every door zone clear, but its pipeline does not constrain windows, which is why it blocks many of them. Its solver also guarantees zero collisions, where Architect-Ant has 0.9%.
We thank the reviewer for the very precise questions. They led us to rebuild both comparisons and to make the paper more consistent.
In the submission, the reasoning runs had larger generation limits for the complex room types with long outputs (6,144 tokens for kitchens, 4,096 for living rooms, 3,072 otherwise). We had assumed that a larger budget would let long reasoning finish. It did not solve the problem. Long rollouts that hit the limit still dominated the update, and the budgets were no longer comparable across variants.
For the revision we matched the budget and changed how over-long rollouts are handled:
The rest of the recipe is identical for both GRPO variants: the same text-only (thanks to reviewer Tb1z) SFT start, data, reward, 8 updates of 8 rooms × 16 rollouts, learning rate, seeds and evaluation.
The main gain comes from rule-guided RL itself, not from reasoning: direct-DSL GRPO with our reward improves the mean over SFT in every room type, significantly in kitchens (+1.10 [+0.24, +2.00]) and living rooms (+0.84 [+0.34, +1.39]; reward ablations, Q3). Whether the model reasons before writing the layout is a secondary choice; its mixed results below concern only that choice, not the gain from the reward.
The new Table 4 reports 8 samples per held-out room; as requested by Reviewer Tb1z, it now also includes dining rooms. Every sample counts, with invalid outputs scored −5, and rooms where all samples failed are included:
(a) Valid % = share of outputs that parse into a layout within the 4,096-token budget.
Do the results still favour reasoning-enabled GRPO? In the matched comparison, reasoning GRPO improves the mean LRS over direct-DSL GRPO in kitchens and dining rooms, and the best-of-8 LRS in bathrooms, with paired 95% confidence intervals excluding zero. It has the highest best-of-8 point estimate in every room type, but the other best-of-8 differences, and its lower means in living rooms and bedrooms, are not statistically resolved. We keep it as the main model for its gains in kitchens and dining rooms and its best-of-8 performance. Its lower means come partially from outputs that do not finish within the token budget; direct-DSL GRPO remains a faster alternative with fewer failures.