- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes ProactGen, a framework for proactive clarification in text-to-video generation. It uses low-cost video drafts to guide a vision-language model in asking targeted questions about missing user preferences. The questioning policy is trained with GRPO using final video-to-reference alignment as the reward. Experiments on InstanceCap-500 and MiraBench-500 show improved alignment over prompt optimization and proactive clarification baselines, while low-cost drafts reduce the computational overhead.
Critical strengths
- The paper addresses a meaningful limitation of current video generation systems: users frequently omit important visual and temporal preferences from their initial prompts. The distinction between automatically rewriting existing information and actively acquiring missing user intent is well motivated.
- The authors evaluate the method on two datasets and compare against several representative baselines, including prompt optimization and proactive clarification approaches. The evaluation includes multiple metrics, ablations on reinforcement learning and draft conditioning, and paired confidence intervals. These experiments provide evidence that the proposed framework improves reference alignment over the evaluated baselines.
Critical weaknesses
- The contribution of draft-grounded clarification is relatively small and not statistically conclusive. One of the paper's central claims is that observing a generated draft enables the questioning policy to select more effective questions. However, Table 2 shows that the RL-trained policy with draft observation achieves a DreamSim-DTW score of 0.678, compared with 0.675 for the independently trained text-only policy. Moreover, A.6 reports a paired difference of only +0.003. While reinforcement learning clearly improves the questioning policy, the independent benefit of draft observation is not convincingly established. This raises concerns about whether introducing the draft generation stage is truly necessary, especially given its additional computational overhead. Since draft grounding is a key distinguishing contribution of the paper, stronger evidence is needed to justify its effectiveness and cost-efficiency.
- The questioning policy does not adequately consider user interaction costs. The paper aims to reduce the burden of iterative video generation by proactively clarifying user intent. However, excessive questioning, especially for simple or sufficiently specified prompts, may negatively affect user experience. This raises concerns about its ability to adapt the questioning granularity to task complexity. Since the reward primarily optimizes final video alignment without explicitly penalizing the number of valid questions, the policy may favor unnecessary clarification. The authors should evaluate the trade-off between question budget and alignment, particularly whether the policy can avoid unnecessary questions for simple tasks.
- Draft-based clarification introduces additional inference overhead compared to the text-only policy (11.13s -> 15.77s in Tab. 4), despite achieving only marginal performance improvements. This raises concerns about its computational efficiency, particularly given the extra costs of draft generation and VLM processing.
- Could the authors provide more examples demonstrating how ProactGen corrects human actions or camera movements? Such examples would help validate its effectiveness on dynamic aspects of video generation.
Questions for authors
Please see the weaknesses for details. My main concerns are the marginal benefit of draft grounding over text-only RL and the lack of consideration for user interaction costs, which raise questions about the effectiveness and practicality of the proposed framework.
4 comments
Rebuttal by Authors (2/4)
W2: The questioning policy does not adequately consider user interaction costs. The paper aims to reduce the burden of iterative video generation by proactively clarifying user intent. However, excessive questioning, especially for simple or sufficiently specified prompts, may negatively affect user experience. This raises concerns about its ability to adapt the questioning granularity to task complexity. Since the reward primarily optimizes final video alignment without explicitly penalizing the number of valid questions, the policy may favor unnecessary clarification. The authors should evaluate the trade-off between question budget and alignment, particularly whether the policy can avoid unnecessary questions for simple tasks.
A2: Thank you for this valuable suggestion. Following your recommendation, we evaluated the question-budget trade-off via prefix truncation (added in Appendix A.9.2, Table 9), examined real-user interaction burden in a human-in-the-loop study (Section 4.5, Table 3), and added a dedicated Limitations section (Section 5) in the main text to discuss adaptive question budgeting for future work:
(2.1) Question-budget truncation curve: To examine how alignment varies with the number of questions, we kept the first questions generated by ProactGen in their original order across all 500 InstanceCap samples and ran consolidation and final generation for each (added in Appendix A.9.2, Table 9):
| Questions kept () | Mean valid answer words | DreamSim-DTW ↑ | 3D-VAE ↓ | DnS ↑ |
|---|---|---|---|---|
| 0 (Direct) | 0 | 0.658 | 144.03 | −0.689 |
| 1 | 5.0 | 0.666 | 143.18 | −0.681 |
| 2 | 9.9 | 0.666 | 143.21 | −0.678 |
| 3 | 14.7 | 0.669 | 142.92 | −0.668 |
| 4 | 19.7 | 0.674 | 142.63 | −0.667 |
| 5 (full budget) | 24.5 | 0.678 | 142.34 | −0.659 |
As shown, alignment improves steadily across all three metrics from to rather than saturating after the first question. However, because the policy is trained to submit up to 5 questions as a single batch without an ordering objective, the learned policy does not order its questions by decreasing importance (for example, questions 4 and 5 still bring clear gains), so this truncation curve does not show a clear trade-off point for post-hoc early stopping.
(2.2) Practical interaction burden and adaptive question counts: While our setup caps answers at 10 words and penalizes invalid questions, the reward does not penalize the number of valid questions, encouraging the policy to ask all 5 questions per round. In our new human-in-the-loop study with 4 participants across 100 targets (Section 4.5, Table 3), where participants were requested to answer in natural language, flag any unanswerable or invalid questions, and rate per-question difficulty and overall mental effort (1–5 ↓), answering a 5-question round remained lightweight in practice: 98.6% of questions were answerable with low per-question difficulty (1.74/5) and substantially lower mental effort than manually revising the prompt from the draft (2.10/5 vs. 4.00/5), while improving final video alignment by +0.021 over Direct. Even so, on prompts that are already simple or sufficiently specified, asking all 5 questions unconditionally can still introduce unnecessary interaction; adapting the number of questions to prompt complexity is an insightful direction that lies beyond the scope of the current paper. Teaching a policy to adjust its question count adaptively requires introducing an explicit question-count penalty into the RL objective and carefully balancing it with the video alignment reward so that the policy avoids unnecessary questions on simple prompts without under-asking on underspecified ones. We have added a Limitations section (Section 5) in the revised main text to highlight this direction and motivate future work.
Rebuttal by Authors (3/4)
W3: Draft-based clarification introduces additional inference overhead compared to the text-only policy (11.13s -> 15.77s in Tab. 4), despite achieving only marginal performance improvements. This raises concerns about its computational efficiency, particularly given the extra costs of draft generation and VLM processing.
A3: Thank you for raising this practical concern. We agree that the text-only policy is faster in a single server-side round (11.13 s vs. 15.77 s in Table 4 of the initial submission, now Table 6 in Appendix A.8); to evaluate efficiency across budgets, we have updated the time–alignment plot in Figure 3 (Section 4.4) to include 1–12 text-only rounds and incorporated measured human answering time in Appendix A.8 (Table 7):
(3.1) Stage breakdown and matched-compute comparison: The +4.64 s single-round server difference comes from the 8-step draft (4.25 s) and VLM visual processing (~0.4 s). To compare both policies visually across compute budgets, we added the 1–12 round text-only curve to Figure 3, with key points summarized below:
| Method | R1 | R2 | R3 | R4 | R11 (Text best) | R12 |
|---|---|---|---|---|---|---|
| Text-only (System time / DS-DTW) | 11.1 s / 0.675 | 15.3 s / 0.681 | 20.0 s / 0.683 | 25.0 s / 0.683 | 62.0 s / 0.686 | 67.4 s / 0.685 |
| ProactGen (System time / DS-DTW) | 15.8 s / 0.678 | 24.7 s / 0.683 | 33.6 s / 0.690 | 42.5 s / 0.692 | – | – |
As shown in Figure 3 and the table above, under server budgets below 20 s, 1–2 text-only rounds are faster, and the two curves cross around 25 s (0.683). Beyond 25 s, Text-only plateaus at 0.686 even after 62.0–67.4 s (11–12 rounds), whereas ProactGen reaches 0.690 in 33.6 s (R3) and 0.692 in 42.5 s (R4), achieving higher alignment in less total compute time.
(3.2) Combined latency with measured human answering time: To evaluate total wall-clock cost with a real user in the loop, we measured an average human answering time of 108.8 s per 5-question round in our human study (Section 4.5, Table 3) and replaced the simulated-user time in Appendix A.8 (Table 6), as reported in Table 7:
| Method & Rounds (Wan2.2 framework) | Server time | Human time | Combined total | DS-DTW ↑ |
|---|---|---|---|---|
| Text-only (1 round) | 8.6 s | 108.8 s | 117.4 s | 0.675 |
| ProactGen (1 round) | 13.2 s | 108.8 s | 122.0 s | 0.678 |
| Text-only (2 rounds) | 10.9 s | 217.5 s | 228.4 s | 0.681 |
| ProactGen (2 rounds) | 19.5 s | 217.5 s | 237.0 s | 0.683 |
| Text-only (3 rounds) | 13.6 s | 326.3 s | 339.9 s | 0.683 |
| ProactGen (3 rounds) | 25.9 s | 326.3 s | 352.2 s | 0.690 |
| Text-only (4 rounds) | 16.7 s | 435.0 s | 451.7 s | 0.683 |
| ProactGen (4 rounds) | 32.2 s | 435.0 s | 467.2 s | 0.692 |
As shown, once user answering time is included, the share of time spent generating the draft becomes very small (+4.6 s is only 3.8% of single-round time). Because ProactGen reaches higher alignment in fewer interaction rounds, the human time saved by avoiding even one extra round far outweighs the cost of draft generation (for instance, 3 rounds of ProactGen save ~100 s of total time over 4 rounds of Text-only while achieving higher alignment).
Rebuttal by Authors (4/4)
W4: Could the authors provide more examples demonstrating how ProactGen corrects human actions or camera movements? Such examples would help validate its effectiveness on dynamic aspects of video generation.
A4: Thank you for this helpful suggestion. We have added multi-frame qualitative examples illustrating how ProactGen corrects human actions and camera movements in Appendix A.9.6 (Figure 5), provided the corresponding full-motion videos at an anonymous page (https://anonymous.4open.science/r/proactgen-case-study-page-1012/index.html), and reported dataset-wide quantitative results on action and camera recovery in Appendix A.9.4 (Table 11):
(4.1) Qualitative examples on human actions and camera movements: We include four examples from our MiniMax-H3 [1] evaluations (Sections 4.5–4.6) as multi-frame sequences in Appendix A.9.6 (Figure 5), comprising two human-action examples (Samples 377 and 148) and two camera-movement examples (Samples 078 and 059). To allow direct inspection of temporal motion in video form, we also provide side-by-side full videos (target reference, low-step draft, Direct baseline, and ProactGen final video) together with the complete initial prompts, question-answer pairs, and refined prompts at https://anonymous.4open.science/r/proactgen-case-study-page-1012/index.html.
(4.2) Quantitative validation on human actions and camera movements: To verify systematic gains on these dynamic aspects beyond individual examples, we evaluate on the same 500 MiraBench samples as in Table 1 using the independent ETVA [2] atomic verification protocol, measuring recovery rates specifically on missing Relation / Action items ( samples) and Camera items ( samples):
| Method (MiraBench-500) | ETVA Relation / Action ↑ | ETVA Camera ↑ |
|---|---|---|
| Direct | 28.6% | 31.5% |
| Text-only (RL, text) | 40.8% | 39.5% |
| ProactGen (1 round) | 42.1% | 41.7% |
As shown, across the full benchmark, ProactGen raises missing relation/action recovery from 28.6% to 42.1% (+13.5 pp over Direct) and camera recovery from 31.5% to 41.7% (+10.2 pp over Direct), outperforming both Direct and the trained text-only policy on both aspects.
References:
[1] MiniMax. (2026). MiniMax H3: An Open Model Breaking the Boundaries Between Tasks and Modalities.
[2] Guan, K., et al. (2025). ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering. ICCV 2025.
Thank you again for your constructive comments; please let us know if you have any further questions.
Rebuttal by Authors (1/4)
We thank the reviewer for the careful and valuable comments. We respond to each concern below:
A1: We thank the reviewer for raising this central concern. We agree that the single-round DreamSim-DTW comparison on InstanceCap (+0.003 [−0.001, +0.007] in
Appendix A.6,Table 3in the initial submission andTable 4in the revision) alone cannot establish the independent benefit of observing a draft. We conducted multi-round interaction experiments and ETVA fine-grained intent recovery evaluation to address it, added toSection 4.4(Figure 3),Appendix A.9.2(Table 8), andAppendix A.9.4(Table 11; cost-efficiency is evaluated in A3):(1.1) Multi-round comparison between draft-based and text-only policies: In the first round, generic questions inferred from the short prompt already yield similar gains (though the 2×2 RL-by-draft interaction is positive at +0.007 [+0.001, +0.012] in
Appendix A.6). To test whether observing the draft is needed as interaction continues, we ran both policies for multiple rounds on the same 500 InstanceCap samples:As shown, the two policies perform similarly in the first two rounds. After Round 2, the text-only policy plateaus and stays between 0.683 and 0.686 from Round 3 to Round 12. In contrast, ProactGen improves in every round, leads from Round 3 with the paired interval excluding zero, and reaches 0.692 in Round 4, surpassing all 12 rounds of the text-only policy. Based on these results, we hypothesize that once common ambiguities are resolved early on, the text-only policy lacks visibility into the video to locate remaining mismatches, whereas updated drafts offer visual cues for later questions. That said, while our experiment establishes the multi-round empirical gain, it cannot conclusively prove this underlying mechanism, which requires finer-grained question-to-error attribution analysis in future work. Thus, while the draft adds little in the first round, its benefit becomes clear across multiple rounds.
(1.2) ETVA fine-grained intent recovery evaluation: To test whether observing the draft already helps capture specific missing details in a single round under a finer-grained metric, we adopt ETVA [1] to decompose full target descriptions into 24,745 atomic verification questions missing from the initial prompt on the same 500 MiraBench samples as in
Table 1(which officially provide structured dense captions):As shown, single-round ProactGen recovers 50.6% of missing intent overall, achieving a statistically significant gain over the trained text-only policy (+1.6%, 95% paired CI [+0.3%, +2.9%] excluding zero), and consistently leads the text-only policy across every component (+3.1 pp on entities, +2.2 pp on camera, +1.3 pp on relations/actions, and +1.1 pp on attributes), showing that inspecting the draft helps target missing visual elements that are hard to guess from the text prompt alone. We evaluate the computational and human-time cost-efficiency of introducing the draft in A3 below.
Reference:
[1] Guan, K., et al. (2025). ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering. ICCV 2025.