- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents a self-improving framework for world action models by utilizing an action refiner to correct local execution deviations. As world action models usually exhibit a stronger video prior than their action generator, this framework triggers action refinement when execution deviates from the predicted visual goal, and combines the corrective trajectories with expert data for further improvement of the WAM. Experiments show the refiner enables performance gains while providing corrective data to support further model finetuning. Overall, the framework demonstrates effective self-improvement over both simulated and real-robot settings.
Critical strengths
- The proposed framework utilizes the stronger prior from video prediction to guide the local correction with a lightweight action refiner, which in general can be integrated with other existing world action models.
- The experiments provide extensive evaluations in the simulated and real-robot environments and showcase a consistent performance trend.
Critical weaknesses
- In Table 1, it seems that all compared methods are fairly saturated on the LIBERO tasks. The FastWAM-joint baseline is merely 0.7 points below the best-performing method on average. The comparisons are less informative without understanding the detailed evaluation protocol (e.g., number of trials and seeds) and the standard error/deviation of the reported numbers.
- The simulated evaluation lacks comparisons with external baselines, such as Latent Policy Barrier[1] or CCIL[2], which can be compared against the proposed WAM+action refiner. It also remains unclear how the proposed self-improvement framework compares against existing self-improving methods (e.g., in terms of efficiency).
- Further clarifications are required for the questions below, particularly for the first two questions.
[1] Sun et al. Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution. 2025
[2] Ke et al. CCIL: Continuity-based data augmentation for corrective imitation learning. 2023
Questions for authors
- What target-state control interface did the authors use in the action refiner? Is it an IK solver? How does the refiner avoid obstacle collisions during corrective execution?
- Given the action refiner formulation, would it be able to serve beyond simply "refinement" purposes? How does the performance compare to the proposed method, if the action chunk predicted by WAM is discarded, and the refiner is used to directly extract the target robot state from the predicted visual goal, which is then fed into the control interface for execution?
- How are and decided for the experiments? How does the relation between and affect the performance?
- Is the action refiner (i.e., the target predictor) frozen during finetuning stages? Would finetuning action refiner bring extra benefits?
- In Figure 3, typo “color gitter” -> “color jitter”
7 comments
Q1.How are the refiner's target states executed, and how are obstacle collisions avoided?
Thank you for this valuable question. A key advantage of DreamChaser is that learned EEF action correction is decoupled from low-level execution, allowing the refiner to work with different robot controllers. On PiperX, we convert predicted corrections into EEF pose targets and use an IK solver to obtain joint commands. In LIBERO, interpolated EEF correction commands are executed by the environment's default operational space controller (OSC).
This modular design supports collision-aware execution with existing motion planners, as demonstrated by our cuRobo[5] integration. The EEF correction is converted into a target pose, toward which cuRobo plans a trajectory using current joint states, robot geometry, and scene obstacles. This integration improves task success without retraining the refiner, highlighting DreamChaser's modularity and extensibility (Table R6).
• Table R6. Correction performance and latency
| Execution | LIBERO-Plus SR (%) | Added latency (ms) |
|---|---|---|
| FastWAM | 72.1 | 0.0 |
| FastWAM + DreamChaser refiner | 76.8 | 11.3 |
| FastWAM + DreamChaser refiner + cuRobo | 77.6 | 65.7 |
Q2.Performance of direct refiner control from predicted visual goals without WAM action chunks
Thank you for this constructive suggestion. We evaluate a video-to-control variant that discards WAM actions and uses the refiner to predict control targets from the current observation and predicted visual goal. On adapted LIBERO-Plus, this variant achieves 38.8% success, compared with 72.1% for FastWAM and 76.8% for DreamChaser (Table R7).
We attribute this difference to their complementary execution scales. The refiner specializes in goal-conditioned local control, learning short-horizon corrections toward predicted visual goals. The Action DiT jointly generates action chunks, capturing motion dependencies for sustained task execution. DreamChaser combines sequential action generation with targeted local correction to benefit from both.
• Table R7. Controller comparison
| Controller | adapted LIBERO-Plus SR (%) |
|---|---|
| FastWAM actions only | 72.1 |
| FastWAM video + DreamChaser refiner only | 38.8 |
| FastWAM + DreamChaser refiner | 76.8 |
Q3.Choosing H and H_R and how their relationship affects performance
Thank you for this valuable question. H determines the WAM replanning interval, while H_R determines correction duration. We choose H_R = 4 as the shortest correction aligned with FastWAM's four-control-step video sampling interval, allowing collected trajectories to be reused in the original self-improvement training pipeline.
On adapted LIBERO-Plus, we compare H = 8, 16, 32 and H_R = 4, 8, 12 using the third-round WAM with the refiner enabled. The default H = 16, H_R = 4 achieves the highest success with shorter episodes than H = 8 (Table R8). Longer corrections reduce success and increase episode time, supporting brief corrections with a moderate WAM execution interval.
• Table R8. Horizons after three rounds on adapted LIBERO-Plus
| H | H_R=4 SR (%) | H_R=4 Episode duration (s) | H_R=8 SR (%) | H_R=8 Episode duration (s) | H_R=12 SR (%) | H_R=12 Episode duration (s) |
|---|---|---|---|---|---|---|
| 8 | 81.6 | 97.28 | — | — | — | — |
| 16 | 81.9 | 78.34 | 81.2 | 80.25 | 80.9 | 82.31 |
| 32 | 79.6 | 72.06 | 78.5 | 74.56 | 77.9 | 76.82 |
Q4.Whether to freeze the refiner during WAM fine-tuning and the benefits of updating it
Thank you for this valuable suggestion. To reduce online training overhead, our original design trains the refiner once on the original demonstrations and freezes it during online improvement.
We also evaluate updating the refiner after each round of collection and WAM training, using expert replay and accepted online state-transition pairs. The settings share the first-round data and WAM checkpoint. Subsequent collections use their respective refiners. Fine-tuning the refiner further improves both WAM-only performance and execution with refinement (Table R9).
• Table R9. Refiner fine-tuning on adapted LIBERO-Plus
| Refiner (SR, %) | Initial | Initial + refiner | R1 | R1 + refiner | R2 | R2 + refiner | R3 | R3 + refiner |
|---|---|---|---|---|---|---|---|---|
| Frozen | 72.1 | 76.8 | 76.8 | 80.7 | 77.8 | 79.3 | 80.1 | 81.9 |
| Fine-tuned each round | 72.1 | 76.8 | 76.8 | 81.2 | 78.3 | 79.7 | 80.5 | 82.4 |
Q5.Correcting the “color gitter” typo in Figure 3
Thank you for spotting this typo. We will correct “color gitter” to “color jitter” in Figure 3 and check the remaining figure labels to improve the clarity and accuracy of the manuscript.
References
[5] Balakumar Sundaralingam et al. CuRobo: Parallelized Collision-Free Robot Motion Generation. ICRA, 2023.
We are grateful for your thoughtful feedback and generous efforts in reviewing our work. Thank you for helping us improve the paper.
Sincerely,
The Authors
Dear Reviewer b9uT,
Thank you for the time and expertise you have generously devoted to reviewing our paper and supporting the research community.
Our responses include additional evaluations, baseline comparisons, and ablation studies, along with clarifications of the evaluation protocol, control interface, and computational efficiency. We hope these additions help address your concerns. When you have an opportunity, we would greatly appreciate your feedback and would be happy to provide any further clarification.
Thank you again for your valuable time and consideration.
Best regards,
The Authors
Dear Reviewer b9uT,
Thank you for your thorough review and constructive feedback. We have carefully considered your suggestions and respond in detail below.
Thank you for highlighting benchmark saturation and evaluation variability. We evaluated LIBERO over five runs with different random seeds, using 50 trials per task in each run, and report mean success, sample standard deviation, and gains over FastWAM (Table R1).
• Table R1. Repeated LIBERO evaluation
Most LIBERO tasks already approach 100% success. Refinement improves performance on tasks that are not yet saturated. The table below highlights the two tasks with the lowest baseline success as examples, with mean success increasing from 89% to 94% (Table R2).
• Table R2. Examples of refinement gains on LIBERO
To assess broader applicability, we evaluate all 24 tasks of the more challenging RoboCasa-GR1 benchmark. Three improvement rounds increase success from 67.8% to 72.0%, compared with 62.2% for vanilla fine-tuning (Table R3). These results support DreamChaser's broad applicability across diverse manipulation tasks and benchmarks.
• Table R3. Full RoboCasa-GR1 evaluation
Note: R1–R3: self-improvement rounds.
Thank you for these valuable suggestions. LPB[1] and CCIL[2] provide complementary approaches to policy robustness through latent-space guidance and corrective data augmentation. We compare both methods on adapted LIBERO-Plus and the three real-robot tasks with the same FastWAM backbone (Table R4). DreamChaser's refiner achieves stronger task performance with less additional training than either baseline, while adding substantially less inference overhead than LPB. These results highlight the effectiveness and efficiency of visual-goal-guided local correction within WAMs.
• Table R4. External policy-robustness baselines
Note: LP: adapted LIBERO-Plus SR (%). Real: normalized score (0–100). Added: latency per correction. Extra train: additional training time.
Compared with self-improvement methods SILVR[3] and Q-Planning[4], DreamChaser achieves larger policy gains with shorter data-collection and filtering time (Table R5). The updated WAM retains these gains when deployed without the refiner. These results demonstrate more effective and efficient self-improvement across both settings. We will include further experimental comparisons and discussion with LPB[1], CCIL[2], SILVR[3], and Q-Planning[4] in the revised manuscript to better position DreamChaser among robust control and robot self-improvement methods.
• Table R5. Comparison with self-improvement methods
Note: Collect time: mean collection and filtering time per round. Training time is matched across methods for fair comparison.
References
[1] Zhanyi Sun and Shuran Song. Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution. NeurIPS, 2025.
[2] Liyiming Ke et al. CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning. ICLR, 2024.
[3] Calvin Luo et al. Self-Improving Loops for Visual Robotic Planning. ICLR, 2026.
[4] Varun Giridhar et al. Beyond Imitation: Self-Improving Robot Policies via Off-Policy Q-Planning. arXiv:2608.21204, 2026.