- Rating
- 3(+1)
- Confidence
- 2(−1)
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes an adaptive execution framework for World Action Models (WAMs) that compares the WAM’s imagined future with the physical rollout. The goal is to avoid error accumulation during long open-loop chunk execution while reducing the number of WAM calls. The authors introduce Future Forward Dynamics Causal Attention (FFDC), a lightweight verifier that estimates whether the remaining WAM-predicted action segment is still reliable, based on the predicted actions, predicted visual dynamics, the current real observation, and instruction-conditioned semantics. The method is evaluated on 50 RoboTwin tasks in simulation and on six real-world manipulation tasks, and the results show the effectiveness of using the WAM’s predicted future for execution verification.
Critical strengths
- The paper addresses an important problem, and the proposed module is simple, lightweight, and intuitive.
- The paper includes extensive ablation studies on the verifier inputs, MoH training, and the decision threshold.
Critical weaknesses
-
Mismatch between the framing and the training data. The paper frames FFDC as future–reality verification. However, a large part of the negative samples is constructed by corrupting demonstration actions (Section 3.3). In these samples, the real observation is consistent with the prediction and only the actions are perturbed. The verifier may therefore learn whether the actions are consistent with the predicted video, rather than whether reality has deviated from the prediction.
-
Possible repeated short chunks in difficult phases. In difficult phases, the verifier may repeatedly reject the new plan, which could lead to repeated replanning with very short chunks and cause the robot to get stuck. The paper does not describe a safeguard for this case or report the distribution of executed chunk lengths.
Questions for authors
-
In the synthetic negatives (Section 3.3), the real observation is consistent with the prediction and only the actions are perturbed. Could the authors evaluate the verifier separately on negatives from failed rollouts and from synthetic corruptions, to clarify whether it detects deviations between reality and the prediction? This is relevant because removing the real observation reduces the success rate only from 76.4% to 72.4% (Table 3).
-
In difficult phases, the verifier may repeatedly reject similar plans, leading to very short chunks and preventing progress. Did the authors observe such cases, and is there a safeguard such as a minimum chunk length or a limit on consecutive replans? The distribution of executed chunk lengths on the hard tasks would help clarify this.
-
Please specify how often the verifier is evaluated during execution and the value of k used for verification.
-
The Abstract and Introduction report differences in percentage points as percentages (e.g., 9.17% and 13.33%). The name “Base-Motus-LC16” is also ambiguous, as it is unclear whether it refers to Base-Motus or to LC-16.
-
Several tables and figures are placed in the middle of the text. Placing them at the top of the page would improve readability.
-
The paper does not provide videos of the real-robot experiments, and Figure 4 shows only a single snapshot sequence.
I am willing to raise my score if those points are addressed.
9 comments
Response to W2 Q2 Q3: Repeated replanning, execution safeguards, and checking frequency, Q4 Q5: Percentage points, baseline naming, and layout, and Q6: Real-robot videos
W2 Q2 Q3: Repeated replanning, execution safeguards, and checking frequency
Thank you for highlighting this concern. We have clarified the verification schedule in Section 3.1, “Preliminary,” and added the detailed execution protocol and chunk-length distributions to Appendix B, “Execution protocol and chunk-length distribution” (Table 5).
The verifier is evaluated every 16 executed action steps: after steps 16, 32, and 48 within a 64-step plan. If the score falls below 0.5, the remaining actions are discarded and replanning is triggered; otherwise, execution continues. Once all 64 actions are exhausted, a new plan is generated if the episode is still ongoing.
The verification horizon is in Eq. (3) and Section 3.2. Each check assesses the next 16 predicted actions.
The analysis of the executed chunk lengths: We additionally analyzed the execution from the clean and randomized evaluations, each covering 50 tasks with 100 episodes per task. The table below reports the executed chunk lengths between successive WAM calls. We exclude each episode’s final chunk because episode termination can truncate it independently of the verifier.
| Setting | Task | Mean chunk length (steps) | chunk 16 (%) | chunk 32 (%) | chunk 48 (%) | chunk 64 (%) |
|---|---|---|---|---|---|---|
| Clean | All 50 tasks | 51.51 | 25.24 | 0.86 | 0.64 | 73.26 |
| Clean | Blocks Ranking Size | 53.13 | 21.25 | 1.74 | 0.70 | 76.31 |
| Clean | Hanging Mug | 42.04 | 44.54 | 0.84 | 1.96 | 52.66 |
| Clean | Place Mouse Pad | 48.67 | 29.17 | 4.17 | 0.00 | 66.67 |
| Clean | Put Object Cabinet | 55.84 | 10.79 | 5.86 | 6.92 | 76.43 |
| Clean | Scan Object | 54.87 | 15.01 | 2.02 | 7.97 | 75.00 |
| Randomized | All 50 tasks | 53.64 | 21.10 | 0.43 | 0.61 | 77.86 |
| Randomized | Blocks Ranking Size | 59.42 | 8.81 | 0.88 | 0.44 | 89.87 |
| Randomized | Hanging Mug | 37.24 | 55.07 | 0.68 | 0.68 | 43.58 |
| Randomized | Place Mouse Pad | 44.44 | 37.04 | 3.70 | 3.70 | 55.56 |
| Randomized | Put Object Cabinet | 55.37 | 11.67 | 6.01 | 6.89 | 75.43 |
| Randomized | Scan Object | 54.63 | 15.22 | 3.88 | 5.17 | 75.73 |
FFDC preserves long execution chunks overall: 73.26% of non-final chunks in the clean setting and 77.86% in the randomized setting reach the full 64 steps, with mean lengths of 51.51 and 53.64 steps, respectively. On Hanging Mug, 16-step chunks are more frequent (44.54% and 55.07%), but 52.66% and 43.58% of chunks still reach 64 steps, yielding mean lengths of 42.04 and 37.24 steps. Thus, FFDC retains substantial long-chunk execution even on this difficult task while allowing earlier replanning. We have clarified the execution protocol and included these distributions in Appendix B of the revised paper. We will investigate recovery mechanisms for persistent replanning in future work.
Q4 Q5: Percentage points, baseline naming, and layout
Thank you for pointing out these issues. We have addressed them in the revised manuscript:
- In the Abstract and Section 1, “Introduction,” we have corrected “9.17%” and “13.33%” to “9.17 percentage points” and “13.33 percentage points,” respectively (lines 024 and 100 of the revised PDF).
- We have consistently renamed “Base-Motus-LC16” to “Base-Motus” throughout the manuscript (see lines 387 and 410 of the revised PDF for the revised name in Section 4.2 and Table 2).
- We have revised the float-placement settings for the main-text tables and figures to favor the top or bottom of pages.
Q6: Real-robot videos
Thank you for this question. We have added a description of the supplementary real-robot videos to Section 4.2, “Real-world experiments,” and provided the videos in the supplementary material. The videos are presented at 1× playback speed, with annotations identifying action execution, WAM inference, and verifier-triggered replanning.
Dear Reviewer Jhu1,
Thank you again for your careful review and constructive feedback. We have provided point-by-point responses to your comments in our replies above.
With two days remaining in the discussion phase, we would be grateful to know whether our responses and additional evidence have adequately addressed your concerns. If you find that our rebuttal and additional evidence have adequately addressed them, we would be deeply grateful for your consideration of revisiting the evaluation. If any questions remain or further clarification would be helpful, we would be happy to continue the discussion.
We look forward to hearing from you. Thank you again for your time and consideration.
Best regards,
The Authors
Response to W1 and Q1: Future–reality framing versus action-corruption supervision
Dear Reviewer Jhu1,
Thank you for your careful review and constructive feedback. Due to the 5,000-character limit per response, we have divided our replies into multiple comments.
W1 and Q1: Future–reality framing versus action-corruption supervision
Thank you for highlighting this concern. We have added the supervision analyses to Appendix A, “Analysis of verifier supervision” (Table 4), with a cross-reference in Section 3.3, “Training strategy and dataset construction.”
Our action-corruption strategy is motivated by a failure pattern observed in our WAM rollouts: predicted visual futures often depict successful execution even when the corresponding actions are incorrect. Corrupting demonstration actions while retaining the original visual context approximates this inconsistency. These synthetic examples are complemented by actual successful and failed rollouts, whose real observations, predicted visual tokens, and executed actions provide supervision for naturally occurring execution discrepancies.
1. To examine explicit visual-mismatch supervision, we additionally train a verifier variant whose synthetic negatives perturb or mismatch only the predicted visual tokens, while keeping real observations and remaining actions unchanged.
The visual-negative variant achieves 88.16% SR, compared with 88.20% for the original FFDC, maintaining comparable downstream performance with an alternative synthetic-negative construction.
2. To directly address Q1, we evaluate the FFDC checkpoint with the fixed threshold of 0.5, without retraining, on two independent test sets. The actual-rollout set contains segments from successful executions and critical failure segments from failed executions. The demo-derived set contains unmodified demonstration segments as positives and synthetically corrupted segments as negatives, generated from demonstration episodes excluded from training. Each set contains 10 positive and 10 negative examples per task under each of the clean and randomized settings, covering all 50 tasks.
The verifier achieves 91.65% accuracy on actual rollout segments, compared with 93.75% on demo-derived samples, a difference of 2.10 percentage points. Its high accuracy on actual executions provides evidence that its classification ability extends beyond recognizing synthetic corruption patterns. We have included the separate classification results, clarified the motivation and composition of the negative training data, and reported the visual-negative experiment in Appendix A of the revised manuscript.