- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper identifies stage confusion in World-Action Models: generated futures may be visually plausible and physically feasible while advancing the wrong task stage. TaskWAM addresses this problem with Mode Tokens for instruction-grounded task requirements, State Tokens for causal execution-progress tracking, and task-state-conditioned steering of world and action generation. The paper also introduces StageBench, a benchmark built from overlapping multi-stage trajectories. Experiments cover StageBench, RoboTwin 2.0, and several real-world manipulation settings.
Critical strengths
-
The research motivation is clearly stated. “Plausible future, wrong choice” is a useful way to describe failures in which local physical plausibility does not imply task-stage correctness.
-
StageBench targets a meaningful gap in existing evaluations. It constructs overlapping observation-action trajectories across tasks and execution stages, which provides a direct way to simulate stage progression.
-
The proposed method is well aligned with the diagnosis. Mode Tokens preserve task requirements, State Tokens estimate progress, and the steering modules inject both into generation. The mapping from problem to architecture is easy to follow.
Critical weaknesses
-
The codebook design for Mode Tokens would benefit from more in-depth analysis. The selection of key parameters, such as codebook capacity, lacks sensitivity analyses or theoretical justification. Do the codebook entries capture interpretable modes? Do codebook configurations vary across task families? These key questions remain unaddressed.
-
The choice of a fixed window length for State Tokens (K = 8) is not sufficiently justified. For longer tasks, are K = 8 interaction slots sufficient to cover the critical execution history? Although the paper demonstrates improvements on long-horizon tasks, it neither analyzes window-length sensitivity nor compares against long-term context modeling methods such as MemoryWAM.
-
The plug-and-play claim is somewhat too strong and needs clarification. TaskWAM is evaluated on two WAM benchmarks and appears to require training or adaptation rather than operating as a purely plug-and-play module. Cross-embodiment results likewise involve platform-specific data and adaptation.
-
StageBench is described as containing 10 task families in the first paragraph of Section 4 and 8 task families in Section 5, which needs correction.
Questions for authors
-
Do the entries in the Mode Token codebook correspond to interpretable modes? Could the codebook be visualized to verify whether it has learned meaningful mode separation?
-
State Tokens adopt a fixed history window of length K = 8. Was this setting derived from hyperparameter analysis? For longer-horizon tasks, might it become a performance bottleneck?
-
The paper notes that stage confusion is not merely a memory-length problem, yet the experiments do not directly compare with memory-based methods such as MemoryWAM. Could such comparisons be added to further verify the advantages of TaskWAM over such methods?
4 comments
Respond to Reviewer sjMN (2 / 2)
- W3: Clarifying the Description of Modular Integration.
Thank you for raising this point. We would like to clarify that TaskWAM's plug-and-play capability refers to modular integration and cross-embodiment adaptation.
Recent works in embodied learning, including CycleManip[1], RoboFlow4D[2], MetaVLA[3], and RC-NF[4], similarly use "plug-and-play" to describe modular components or frameworks that involve training or adaptation, without implying training-free deployment. TaskWAM follows this architectural usage: we retain the same core task-state grounding and steering design across Fast-WAM and Cosmos Policy, as well as the evaluated robotic platforms. Integration uses backbone-specific training and platform-specific data and input/output interfaces, without redesigning the proposed grounding and steering mechanisms.
We appreciate you for prompting us to make this scope explicit. We have refined the descriptions in the introduction and experimental sections to clarify modular integration across heterogeneous WAM architectures and cross-embodiment adaptation with platform-specific interfaces, specifying the associated training and integration procedures. Our claim concerns architectural modularity and adaptability, rather than training-free transfer of a single checkpoint across arbitrary backbones and embodiments.
[1] Wei Y L, et al. "Cyclemanip: Enabling cyclic task manipulation via effective historical perception and understanding." CVPR 2026.
[2] Lin, Sixu, et al. "Roboflow4d: A lightweight flow world model toward real-time flow-guided robotic manipulation." ICML 2026.
[3] Li, Chen, et al. "Metavla: Unified meta co-training for efficient embodied adaptation." ICLR 2026.
[4] Zhou, Shijie, et al. "RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation." CVPR 2026.
- W4: Typos in Section 4 and Section 5.
Thank you for pointing this out. We have corrected the typo so that Sections 4 and 5 consistently report eight StageBench task families.
- Q3: Additional comparisons with memory-based baselines.
Thanks for highlighting these related works. To the best of our knowledge, open-source training resources for memory-based WAMs remain limited at the time of this response, with MemoryWAM’s official training code not yet publicly released. We have therefore added a comparison with MemoryVLA[1], a recent memory-based manipulation policy with an available training implementation. We additionally include a matched-history baseline (i.e., TaskWAM without Structured State Encoding) for WAM-level pair comparisons. This baseline retains the same history inputs and Mode Token branch, providing a complementary comparison within the same backbone.
| Method | Cooking & Cheese | Cooking & Juice | Cooking & Cleanup | Cooking & Breakfast | Size-Order Cubes | Color-Order Cups | Arm-Assigned Hammering | Repeated Bread Cutting | Avg. Suc. |
|---|---|---|---|---|---|---|---|---|---|
| MemoryVLA | 33 | 28 | 16 | 30 | 44 | 32 | 79 | 61 | 40.4 |
| Matched-history baseline | 68 | 72 | 64 | 63 | 60 | 48 | 80 | 46 | 62.6 |
| TaskWAM (ours) | 74 | 78 | 72 | 73 | 65 | 54 | 83 | 56 | 69.4 |
TaskWAM achieves 69.4% average success on StageBench, compared with 40.4% for MemoryVLA and 62.6% for the matched-history baseline. These additional results extend our evaluation to memory-based alternatives and further support the effectiveness of TaskWAM, including the benefit of structured state encoding under matched history inputs. We have incorporated these comparisons and the corresponding discussion into the revised experimental section.
[1]Shi, Hao, et al. "Memoryvla: Perceptual-cognitive memory in vision-language-action models for robotic manipulation." ICLR 2026.
Dear Reviewer,
I hope this message finds you well. As the discussion period is nearing its end, I wanted to ensure we have addressed all your concerns satisfactorily. If there are any additional points or feedback you'd like us to consider, please let us know. Your insights are invaluable to us, and we’re eager to address any remaining issues to improve our work.
Thank you for your time and effort in reviewing our paper!
Dear Reviewer sjMN,
As the discussion period draws to a close, we would like to briefly follow up on our rebuttal and revised manuscript. We would greatly appreciate your feedback on the additional experiments and clarifications.
If these additions have addressed your main concerns, we would be grateful if you would consider revising your rating upward. We remain available to clarify any outstanding questions.
Thank you again for your time and thoughtful consideration.
Respond to Reviewer sjMN (1 / 2)
Dear Reviewer sjMN, we sincerely appreciate the time and effort you’ve invested in evaluating our work. We have prepared comprehensive experiments and clarifications to address each point you raised. We hope these responses can resolve your concerns and look forward to further discussion.
Thanks for your insightful suggestions. We have added a sensitivity analysis over Kprior∈{4,8,16,24}, where Kprior denotes the number of codebook entries, together with complementary visualizations of Mode Tokens.
(1). Sensitivity to codebook capacity.
As shown below, success on StageBench improves from 63.5% at Kprior=4 to 69.4% at Kprior=16, with no further improvement at 24. These results suggest that increasing codebook capacity is beneficial up to a point, while additional entries do not necessarily improve performance. We therefore use Kprior=16 as our empirical default among the evaluated configurations.
(2). Visual analysis of codebook and Mode Tokens.
To provide more in-depth analysis of Mode Tokens in capturing fine-grained task requirements, we generate 100 unseen, semantic-preserving paraphrases for each task variant through lexical and syntactic rewrites. We then analyze both codebook activation and the resulting grounded Mode Token representations.
The codebook activation visualization (Fig. 4) shows that activation patterns vary with task requirements, while some entries are reused across task families, supporting requirement-dependent routing and cross-family code reuse. The t-SNE visualization of grounded Mode Tokens (Fig. 15) further shows that paraphrases expressing the same execution requirements generally form variant-specific clusters while different task variants remain distinguishable.
These visualizations illustrate the complementary roles of shared codebook priors and instruction-specific grounding, providing qualitative evidence of Mode Tokens distinguishing fine-grained task requirements for stage progression. The details and results can be found in the revised version (Section 5.3 and Appendix C.5). We appreciate the reviewer’s suggestions for helping us uncover this additional strength of our method.
Thanks for raising this point. We have added a sensitivity analysis over K∈{2,4,8,16} On StageBench, where K is the number of recent action-obeservation interaction slots used to construct State Tokens.
(1) Sensitivity to history-window length.
As shown below, success improves from 64.3% at K=2 to 69.4% at K=8, but decreases to 66.8% at K=16. This non-monotonic trend shows that simply extending the history window does not necessarily improve execution tracking, consistent with observations in MemoryVLA[1], CondenseVLA[2], and Long-WAM[3]. A possible explanation is that longer windows introduce redundant or less relevant interactions, making task-critical execution cues harder to distinguish. These results support our default choice of K=8, achieving the best performance among the evaluated configurations.
(2) Continuously updated history for long-horizon execution.
Regarding long-horizon execution, the history window is updated after each executed action chunk, allowing State Tokens to incorporate new execution evidence throughout the task. Thus, State Tokens operate as a compact and continuously updated sliding window rather than storing the entire episode history.
Our long-horizon evaluations provide complementary evidence, including multi-stage StageBench tasks and real-world manipulation such as the nearly two-minute Bread Toasting & Spreading task. Together, the window-length ablation and long-horizon evaluations support that K=8 as an empirically effective history window for reliable stage progression under our evaluated settings.
[1] Shi, Hao, et al. "Memoryvla: Perceptual-cognitive memory in vision-language-action models for robotic manipulation." ICLR 2026.
[2] Hong, Feiyang, et al. "CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA." arXiv preprint 2026.
[3] Huang, Wei, et al. "Long-WAM: Scaling the Context of World-Action Models." arXiv preprint 2026.