- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
PrimLLM generates editable assemblies of cubes, cylinders, and spheres as executable HTML/Three.js programs. An external language model expands an object description into a component-level caption. A 9B generator is supervised on existing primitive assemblies and then optimized with GRPO using format, geometric plausibility, and multi-view visual rewards. In experiment, the reported gains over the base model are substantial, particularly in executable-output rate and structure scores. The contribution is promising, but stronger controls are needed to isolate the value of RL from planning, templates, and candidate search, and to establish stable structural improvements over strong baselines.
Critical strengths
- The representation supports execution and editing. Generating primitive programs provides a direct route to rendering, parameter modification, and outcome-based feedback. Using SFT to establish valid outputs before RL is well motivated.
- The improvement over the base generator is obvious.
Critical weaknesses
- The comparison does not fully separate post-training gains from the effects of external planning, program scaffolding, and inference configuration.
- The evidence for superiority over the strongest baseline is weaker than the evidence for improvement over the base model.
- The supported adaptation claim is narrower than unrestricted annotation-free learning or zero-shot category generalization.
Questions for authors
- Can the authors provide a per-baseline protocol covering original versus planned descriptions, fixed prefix, output length, candidate count, reasoning settings, and primitive filtering?
- How does RL compare with SFT+planning and reward-based best-of-N under a matched online generation or evaluation budget?
- What is the quality–cost trade-off between RL and reward-guided search over the same Stage-1 model? It is preferred to report generation, rendering, and scoring costs separately.
- If the intended claim extends beyond label-free category adaptation, can the authors evaluate categories or component compositions absent from both SFT and RL?
Thank you for the insightful comments. Below, we respond to the questions and provide more results. All of them will be included in the revised paper.
Q1: Provide a per-baseline protocol.
A1: We provide the testing code for each baseline in the supplementary material. All baselines receive the same original user description as input and use the same fixed program prefix, generating code only after this prefix. Each description yields one candidate. The baselines use either API-based inference or local deployment, with configurations summarized in the table. To ensure a fair comparison, all models are prompted to use only cubes, spheres, and cylinders. Unsupported primitives are removed through a common post-processing step before rendering and evaluation.
Q2:How does RL compare with SFT+planning and reward-based Best-of-N?
A2: To clarify the contributions of RL over SFT+planning(Stage-1) and reward-based Best-of-N(BoN) selection, we evaluate four settings: Stage-1 with a single output(N=1), Stage-1 with BoN(N=8), Stage-1+RL with a single output(N=1), and Stage-1+RL with BoN(N=8). BoN scores candidates using the same reward models and weights as RL and selects the highest-reward candidate. The results are summarized below:
1. Stage-1 vs. Stage-1+RL: Introducing RL improves performance beyond SFT+planning. This indicates that reward-based RL helps the model explore better primitive compositions and spatial configurations, improving structural plausibility and semantic consistency. The ablation results in Table 2 of the main paper also support this benefit.
2. Stage-1+BoN vs. Stage-1+RL: From the same Stage-1 checkpoint, RL outperforms inference-time reward-based selection. This indicates that the performance gains stem not only from reward-based selection but also from incorporating reward feedback into model parameter updates, improving the model's single-sample generation capability.
3. Stage-1+BoN vs. Stage-1+RL+BoN: With the same candidate count and reward-scoring procedure, Stage-1+RL+BoN still performs better. This suggests that RL provides additional benefits under matched online candidate-generation and reward-evaluation budgets.
Q3: What is the quality–cost trade-off between RL and reward-guided search?
A3: We further compare the inference costs, reporting generation time, generated tokens, rendering and scoring time per prompt. As shown in the table and supported by the results in Q2, BoN improves generation quality at higher inference cost without updating the generation policy. In contrast, RL learns a better policy through a one-time additional offline training stage, yielding higher quality than BoN at lower inference cost. Furthermore, RL supports adaptation to categories unseen during SFT using a small number of training samples and steps, without requiring additional annotations.
Q4: Evaluate the categories that are absent from both SFT and RL.
A4: We understand the reviewer’s concern about zero-shot category generalization. Our contribution is adaptation to SFT-unseen categories through annotation-free RL. We also explore generalization to categories unseen during both SFT and RL. Specifically, we select four such categories, yielding 40 test samples, and compare the baseline, Stage-1 SFT, and Stage-1 SFT+Stage-2 RL models.
As shown in the table, Stage-1 SFT improves HTML Valid and Structure Score, indicating that it helps the model acquire transferable text-to-primitive assembly capabilities. However, as SFT relies on imitation learning, its generalization remains constrained by limited training data. Stage-2 RL further improves all metrics and surpasses the baseline, suggesting that reward-driven RL can complement limited supervision and improve primitive assembly policies. These results also provide preliminary evidence that RL may promote generalization to categories unseen during both SFT and RL.