- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes using the temporal distance representations, a graph of offline experiences, and a critic in combination with LeWorldModel to improve planning performance. The authors also propose switching the cost from temporal distance to LeWM’s L2 distance near the goal. The paper also investigates why LeWM’s latent L2 distance fails at longer horizons and compares the results to LeWM and other baselines in three environments and provides ablation studies showing the effects are dependent on the environment. It provides progress and convergence bounds under model, search and critic error conditions.
Critical strengths
The analysis of using L2 latent distance for long-horizon planning showing that at 50 steps the distance between two states is close to distance between two random points is interesting. The theoretical explanation of why the distance between two samples from isotropic gaussian concentrates so L2 cannot rank them and why the straight path leaves distribution is useful. The same issue likely applies to other models with gaussian-regularized latents.
Critical weaknesses
The method combines components from GAS (temporal distance representations, offline graph) with using MPC in LeWM and standard reachability critic as a planning cost. ALPS (Shehmar et al. 2026) and PcLast (Koul et al. 2024) already combine cluster-based planning and CEM. The contribution therefore is mainly showing that this specific combination adds value, i.e. outperforms other methods and all of its components synergize.
-
The comparison to the prior works is very weak. The LeWM baseline was introduced in the paper whose main contribution was a world model. It evaluated on 25 steps and it never claimed long-horizon planning. The learned GCIQL baseline scores below random policy on Reacher task, which suggests that the baseline is misconfigured. At very least the paper should compare to training GAS on frozen LeWM latents (to show that world model contributes beyond supplying latents) and to training-free planning methods using L2 latent distance similar to SoRB (Eysenbach et al. 2019) or TTGS (Opryshko et al. 2026) to show that L2 distance, shown to be reliable on short horizons, is not sufficient for planning on its own. Comparisons to other similar works (ALPS, PcLast) would strengthen the contribution.
-
The ablation studies do not show that this combination of components is particularly useful. Out of three tested environments, on one (Cube) the temporal distance outperforms the full method, on another one (Push-T) critic provides the majority of the cross-episode gain, and Reacher has no component ablations.
Questions for authors
- Can you compare your method to the related works?
- Can you show the necessity of all components?
- Does your method work with different world models, did you test other design choices?
4 comments
Response to Reviewer y1UL [2/2]
W2 / Q2: Necessity of all components
General Response 2 removes each component from the full method in turn on Push-T. Every removal lowers cross-episode success, by 2.8 to 25.2 points. The critic matters most (−25.2 on cross-episode goals, −15.6 at same-ep 100). The graph, the local switch, TDR subgoal scoring and the ET form each cost 6 to 8 points on cross-episode goals. The graph and the switch help mainly together: each adds about 1 point alone and 8.4 together.
W2: The critic provides most of the gain
The reviewer is correct that the critic gives the largest single gain on Push-T cross-episode goals (14.4 → 31.6 when added to L2). Reachability critics are not new. TDM and RC-aux condition reachability on a step budget. Our contribution is in how the critic is shaped and combined. We score each candidate by its expected hitting time, capped at the remaining budget, and add this to the graph subgoal cost inside CEM. Because CEM keeps candidates by rank, the shape of the critic only matters when it is combined with another term. Our ablations show that scoring by −log V, the negative log-probability of reaching the goal in time, is 8.0 points lower on cross-episode goals, and querying a fixed budget instead of the remaining one changes success by −4.4 to +0.8 points. The remaining components (TDR cost, graph subgoals and L2 switch) add a further 10.8 points over L2 + critic (31.6 → 42.4, a 34% relative gain): 3.2 from the TDR cost and switch, and 7.6 from the graph. The full method is also 11.6 and 8.0 points higher than L2 + critic at same-ep 50 and 100.
W2: TDR alone is better on Cube
On Cube, TDR alone exceeds the full method because no planner grasps an unheld cube: all success is a short carry finished within 50 steps, and the graph's first subgoal delays it. On Push-T, where goals need long plans, our method keeps gaining to the end of the budget (General Response 4).
W2: No component ablations on Reacher
We have now run matching ablations on Reacher. The results are as below, with the rows matching the configurations in the Push-T table.
| Configuration | same-ep 25 | same-ep 50 | same-ep 100 | cross-ep |
|---|---|---|---|---|
| L2 (LeWM) | 77.2 ± 5.4 | 90.8 ± 1.1 | 82.8 ± 1.1 | 29.2 ± 2.7 |
| (a) TDR cost | 76.0 ± 9.3 | 94.4 ± 1.7 | 91.2 ± 0.0 | 48.4 ± 1.4 |
| (b) graph subgoal | 71.6 ± 5.0 | 91.6 ± 3.0 | 90.8 ± 0.0 | 60.8 ± 0.9 |
| (c) (b) + switch | 71.2 ± 4.6 | 91.6 ± 3.0 | 93.2 ± 1.1 | 66.0 ± 1.1 |
| (d) L2 + critic | 74.0 ± 7.3 | 98.0 ± 2.4 | 95.6 ± 0.0 | 53.2 ± 3.8 |
| (e) (b) + critic | 76.4 ± 3.7 | 96.4 ± 0.9 | 94.0 ± 0.9 | 64.0 ± 2.3 |
| (f) (c) + −log V critic | 71.6 ± 4.3 | 94.8 ± 3.6 | 95.6 ± 0.0 | 63.6 ± 0.0 |
| (h) (g), L2 subgoal score | 78.0 ± 5.8 | 97.2 ± 1.7 | 96.4 ± 1.1 | 64.4 ± 1.7 |
| (i) TDR + critic | 78.4 ± 4.6 | 96.8 ± 0.0 | 95.2 ± 0.0 | 59.6 ± 2.6 |
| (j) (i) + switch | 81.6 ± 3.8 | 97.6 ± 1.8 | 96.0 ± 0.0 | 60.4 ± 2.0 |
| (k) TDR + switch | 75.6 ± 5.2 | 96.0 ± 2.0 | 95.6 ± 0.0 | 64.4 ± 1.4 |
| (l) (g), fixed 50-step critic | 75.6 ± 5.0 | 96.8 ± 1.7 | 97.6 ± 0.9 | 62.4 ± 2.4 |
| (g) Full method | 76.0 ± 5.1 | 98.0 ± 1.4 | 97.6 ± 0.9 | 65.6 ± 2.2 |
- Every configuration exceeds L2 at same-ep 100 and on cross-episode goals. At same-ep 25 all rows are within seed noise of L2.
- As on Push-T, removing the graph from (g) lowers cross-episode success (−5.2, (j)), and ET is above −log V (−2.0, (f)).
- Unlike in Push-T, the role of the critic is lower. We attribute this to Reacher being an obstacle-free reach with mostly reversible actions. Thus any cost that still ranks states at long range suffices.
Q3: Other world models and design choices
We did not test other world models, which is a limitation of the current study. As the reviewer notes, the concentration argument applies to any latent regularised towards an isotropic Gaussian, so we expect the L2 failure to recur; we have not tested whether our fix transfers. Within LeWM we varied the critic form (−log V is 10.8 points lower at same-ep 25 and 8.0 lower on cross), budget-aware vs fixed-horizon critic, critic weight, and graph radius.
In summary, the method changes only the planning cost of a frozen LeWM, raises cross-episode success in all three environments, and remains best on cross-episode goals against the added planners. We believe these additions address the soundness concerns in W1 and W2, and we would welcome a reassessment of the score in light of them. We are glad to answer any further questions.
Reviewer's reply
Thank you for engaging in the rebuttal process. I have read through your replies and I maintain my score.
My concerns were not sufficiently addressed.
- The comparisons to prior work are not sufficient to justify your method. If I understand correctly, the baseline table in General Response 1 uses one environment (Push-T), and your method is outperformed by SAGE in all same-episode settings and leads only in the cross-episode setting, which the compared planners do not evaluate.
- The Reacher ablations don’t clearly show that all components are useful. The cross-episode success rate (which you pose as the main metric) is higher for graph + switch without the critic, and TDR + switch alone is within 1.2 points of the full method.
- The whole empirical part relies on 3 environments, of which one has success only on the tasks that “start with the cube held and are short carries”.
- GAS remains a close method, and preliminary experiments, while a valuable source of intuition, might have used a different set of hyperparameters or have other confounding factors. They don’t replace a clean comparison.
- The time-to-goal ranking and AUROC scores, computed over pairs at arbitrary distances, do not establish that L2 distances are insufficient to distinguish between close (reachable) and distant pairs of states, which might be sufficient for graph-based planning methods.
- There were no changes to the paper to improve presentation or add the new experiments.
Thank you for the time you put into your responses.
We thank Reviewer y1UL for following up and reviewing our responses. We respect the reviewer’s perspective and maintain this brief clarification:
-
Cross-Episode Stitching vs. Same-Episode Playback (SAGE Comparison): Same-episode evaluation tasks are sampled from within single demonstration trajectories, functioning largely as trajectory-following or imitation tasks where SAGE’s learned action prior excels. However, the core challenge of long-horizon planning in offline datasets is cross-episode composition (reaching unseen goals across disjoint trajectories). In this true long-horizon setting, which neither SAGE nor Hi-LeWM originally evaluated, our method achieves 42.4% success, outperforming the best SAGE variant (27.2% with its action prior, 31.6% with LeWM CEM) by +10.8 to +15.2 points, and Hi-LeWM by +20.8 points.
-
Reacher Ablations & Inductive Biases Across Environments: On Reacher, the scores for the full method (65.6 ± 2.2), graph + switch (66.0 ± 1.1), and TDR + switch (64.4 ± 1.4) are all within mutual standard error. Reacher is an obstacle-free and fully reversible planar arm task. Distance to goal is monotonic and reachability failures are minimal. A->B can be achieved just as easily as B->A for states A,B. This is unlike Push-T where pushing the block can be achieved much quicker than 'pulling' the block. This necessitates a quasimetric distance function that is provided with TDR+critic. However, any well-calibrated symmetric distance function suffices for Reacher, reducing the necessity of the critic.
Each component provides inductive biases tailored to distinct physical bottlenecks.
-
Benchmark Scope (3 Environments): Push-T, Reacher, and Cube (OGBench) represent the evaluation suite introduced by the LeWorldModel paper that we build on. On Cube, zero-shot visual grasping without task-specific fine-tuning remains an unsolved challenge across all latent MPC planners (all baselines achieve 0% on ungrasped tasks). Such an action sequence has no support in the dataset, and these tasks are an expected quirk of random sampling for cross-episode tasks. On the remaining held-out manipulation tasks, our method improves over vanilla LeWM from 16.4% to 27.6%, and up to 48% using action retrieval.
-
Distinction from GAS (Model-Based MPC vs. Model-Free Policy Learning): We agree with the reviewer that our preliminary policy experiment is not a substitute for a fully tuned benchmark sweep of GAS. However, we hope to clarify the paradigm difference: GAS (Baek et al., 2025) is a model-free hierarchical offline RL method that learns a parameterized goal-conditioned actor policy to reach graph subgoals without a world model. In contrast, our work explicitly studies model-based visual MPC: we keep the visual world model completely frozen and optimize actions online through forward simulation (CEM) with zero policy training. Because our contribution is repairing test-time visual world-model planning, the directly matched baselines are hierarchical and subgoal planners evaluated on frozen world models (SAGE, Hi-LeWM, PCLaSt, and ALPS), which we evaluated on the same offline data, latent encoder, and tasks.
-
L2 vs. TDR for Graph Construction (SoRB / TTGS Comparison): The reviewer asks whether latent L2 thresholding could suffice to identify locally reachable neighbors for graph construction (as in SoRB/TTGS), avoiding the need for a learned TDR. In visual domains with contact dynamics (e.g., Push-T), latent L2 reflects visual/pixel similarity rather than dynamical reachability: two states can share high visual overlap (small L2) while being separated by contact boundaries (e.g., the pusher on opposite sides of the block, requiring a 40-step circumnavigation). Thresholding L2 creates spurious edges across kinematic barriers.
While AUROC or time-to-goal rankings only provide an indication of such restrictions of L2, the component-wise ablations (General Response 2), show that using L2 for graph construction vs TDR ((h) vs. (g)) decreases success rate across all same-episode and cross-episode goals. This confirms the importance of TDR distances.
-
Manuscript Revisions: External baselines for all 3 environments, and all newly generated experiments including the 4 external baselines (SAGE, Hi-LeWM, PCLaSt, ALPS), the compute-matched controls, the Reacher ablation suite, and the graph reachability tests will be included in the final version of the paper.
We thank the reviewer once again for their time and constructive critiques throughout the review process.
Response to Reviewer y1UL [1/2]
The reviewer finds the analysis of latent L2 concentration interesting and useful, but raises three concerns: (1) the comparison with prior work is weak, including the LeWM and GCIQL baselines and the absence of GAS, SoRB/TTGS, ALPS and PCLaSt; (2) the ablations do not show that every component is needed, given the Cube result and the absence of Reacher ablations; (3) whether the method works with other world models and design choices.
We thank the reviewer for the careful reading. Shared experiments are in the General Response.
Scope of the contribution
We agree that the components build on prior work (Sec. 2). Alongside the combination, the paper gives a diagnosis of why terminal L2 fails at long range (Sec. 5.3, App. E–F), which the reviewer notes may extend to other Gaussian-regularised latents, and an analysis of the resulting objective under model, search and critic error (Thms 1–3). The evaluation also includes cross-episode goals, which the compared planners do not report.
W1 / Q1: Comparison to related work
We added SAGE, Hi-LeWM, PCLaSt and ALPS on Push-T with the same tasks, budgets and success test (General Response 1). Our method is best on cross-episode goals (42.4 vs at most 31.6 for SAGE and 21.6 for Hi-LeWM). SAGE is best on same-episode goals, with or without the true state.
Training-free planning with L2 distances (SoRB, TTGS). We did not run these. We measured the distance they would rely on. On held-out pairs, latent L2 ranks time-to-goal worse than our graph distance (Spearman 0.81 vs 0.92). On cross-episode pairs checked in the simulator, L2 predicts reachability only modestly above chance (AUROC 0.56–0.62, against 0.75–0.78 for graph distance). This supports the reviewer's point that L2 is reliable only at short range.
W1: The LeWM baseline is weak
We agree that LeWM was not designed for long-horizon planning. We therefore added four long-horizon planners (General Response 1); Ours is best on cross-episode goals, 10.8 points above the best SAGE variant and 20.8 above Hi-LeWM. LeWM remains in the table as the planner our method modifies, and our analysis of its latent space (Sec. 5.3, App. E) shows why L2 alone fails at long range.
W1: GAS on frozen LeWM latents
In a preliminary experiment on an earlier task set, we trained GAS (TDR, graph and low-level policy) on the same frozen LeWM latents and offline data. Its learned policy came close to the random floor on cross-episode goals and was well below the L2 baseline at longer same-episode offsets. This suggests that planning through the LeWM predictor contributes beyond supplying the latent space.
W1: GCIQL is below random on Reacher
The LeWM paper (Maes et al. 2026) reports no GCIQL result on Reacher (Table 1(B), "--"), so there is no published reference for this setting, and we do not use the Reacher GCIQL row as evidence for our method. On Push-T and Cube, GCIQL uses the configuration of LeWM's baselines (Sec. 5.1). Our task set is harder, since it rejects pairs already solved at the start, so absolute numbers differ from the published ones. GCIQL's performance relative to the random policy is consistent across papers for Push-T and Cube.
Part 2 covers the ablations and other world models.