- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper represents each action by an AND/OR energy tree and permits any internal subtree to be evaluated either explicitly or through a learned macro-energy on the same scale. Wake-sleep training distills expanded energies and learns contraction-error estimates. At inference, propagated estimates and action margins determine which frontier node to expand and when to stop. The winner-preservation result is conditional on error coverage or sufficiently small remaining undercoverage. Across 17 tasks/layouts in BabyAI, MiniHack, and Overcooked-AI, mixed-resolution inference uses roughly 51-78% fewer explicit expansions than the same-checkpoint Full evaluator while retaining similar macro success. Fixed expert-state timing shows lower action-selection latency; separate closed-loop audits quantify early-stop disagreements.
Critical strengths
- The common-energy interface provides a coherent mechanism for local adaptive computation. A macro-energy approximates a particular expanded subtree, so mixed-resolution evaluation has a precise target rather than switching between unrelated policies. The propagation argument and margin condition make the approximation's role in action selection explicit. Importantly, the paper correctly describes learned radii as estimates and the preservation result as conditional.
- The matched-checkpoint Full comparison and the allocation controls provide useful evidence for the mechanism. Across six training seeds, success remains close to Full while expansions decrease substantially. Appendix D's RF-order + Stop control further separates where to expand from when to stop: comparable success requires more expansion under random ordering. Measured fixed-state latency and the closed-loop reliability audit complement expansion counts. These controls support a weak-acceptance recommendation for the local computation-allocation contribution within the stated structured setting.
Critical weaknesses
- Deployment reliability is less settled than the high agreement reported on held-out expert states might suggest. Among closed-loop early stops, Full-winner disagreement is 6.09% on BabyAI and 2.81% on MiniHack (Table 1). The conditional proposition does not provide an operational error-rate guarantee because its residual conditions are post-hoc quantities. The retained BossLevel test is encouraging, but largely falls back to expansion of 32.52/34 nodes and excludes unseen skills. Thus the evidence for simultaneously retaining substantial speedups and reliable stopping under shift remains limited.
- Applicability depends on supplied task-specific AND/OR scaffolds and, for BabyAI/MiniHack, upstream subgoal and consequence interfaces. The controls fairly share these inputs, so this does not invalidate the within-scaffold comparison. However, independent scaffold construction is evaluated on only one task, and fixed-state timing excludes high-level planning and consequence generation. The current evidence therefore establishes savings inside a structured action evaluator more strongly than end-to-end efficiency or robustness across scaffold constructions. This is the principal limitation on the broader significance of the result.
Questions for authors
- On the existing closed-loop evaluation states, what wall-clock savings accompany the early-stop disagreements, and are the disagreements concentrated in particular tasks or failure-critical decisions? Relating these quantities would clarify the actual reliability-efficiency trade-off.
- Can a small sweep of a conservative radius multiplier, using held-out validation choices, show how stopping disagreement, success, and expansion change? This would indicate whether the deployment trade-off is controllable without relying on unobservable residuals.
- For the independently constructed scaffolds in Appendix L, how variable are expansion savings and stopping reliability in addition to success? Please also state what fraction of end-to-end decision time is represented by the evaluator timing, if those measurements are available.
6 comments
Response to Reviewer WF3A (2/3)
Q2. Can a conservative radius multiplier control the reliability–efficiency trade-off?
To examine whether stopping reliability can be adjusted without changing the inference mechanism, we conducted a radius-scaling experiment by multiplying the predicted radii by a factor , giving . Increasing makes the stopping condition more conservative, requiring additional expansion before a decision can be certified. This allows us to examine how early-stop disagreement, expansion, and closed-loop success change as the stopping criterion becomes more conservative. At , all metrics reproduce the main results.
| Metric | λ=1 | Intermediate | λ=5 |
|---|---|---|---|
| Early stopping (%) | 78.08 | 63.28 | 47.66 |
| Early-stop disagreement (%) | 6.09 | 3.24 | 2.03 |
| Expansion (% Full) | 49.12 | 68.11 | 88.19 |
| Closed-loop success (%) | 87.42 | 88.67 | 89.03 |
Six-task macro averages; disagreement is conditional on early certification. The intermediate setting uses λ=2 for four tasks and λ=1.5 for the two UnlockPickup tasks.
Takeaway. Increasing the radius multiplier reduces early-stop disagreement from 6.09% to 2.03%, while expansion increases from 49.12% to 88.19% of Full. Closed-loop success also increases from 87.42% to 89.03%. These results show that the reliability–efficiency trade-off can be adjusted through radius scaling: more conservative stopping reduces disagreement at the cost of additional computation. We have added the radius-scaling experiments and their reliability–efficiency analysis to Section 4.4 and Appendix F of the revised manuscript.
W2 / Q3. Independent scaffolds and evaluator fraction
Q3(a). How variable are expansion savings and stopping reliability across independently constructed scaffolds?
To address your concern about whether our method depends on particular predefined scaffolds, we extended the independent construction experiment in Appendix L. For the same BabyAI UnblockPickup task, we independently generated three AND/OR scaffolds with 29, 32, and 33 internal nodes. We then evaluated each scaffold using six independent training and evaluation, following the main benchmark protocol, to examine whether the expansion savings and stopping behavior remain consistent across different structures and training runs. Within each run, Full and Ours share the same scaffold and trained checkpoint, ensuring a matched comparison.
| Nodes | Full success (%) | Ours success (%) | Expansion (% Full) | Early stopping (%) | Disagreement (%) | Residual-valid (%) | Realized-valid (%) |
|---|---|---|---|---|---|---|---|
| 29 | 83.00±2.97 | 80.67±1.86 | 42.86±4.35 | 98.61±0.67 | 8.52±4.11 | 80.24±6.61 | 87.80±4.91 |
| 32 | 85.17±2.23 | 84.50±3.78 | 50.37±2.22 | 99.05±0.50 | 4.61±2.73 | 91.43±2.90 | 94.46±3.00 |
| 33 | 88.83±2.56 | 87.00±3.10 | 39.70±5.53 | 99.41±0.70 | 8.90±5.43 | 81.88±7.12 | 87.65±7.15 |
Mean ± SD across six seeds. Early stopping uses all audited decisions, while disagreement and validity rates are conditional on early certification.
Takeaway. Across the three independently generated scaffolds, Ours reduces explicit expansion by 49.63–60.30%, while maintaining success within 0.67–2.33 percentage points of Full. Early-stopping rates remain above 98%, while disagreement rates vary from 4.61% to 8.90%. These results show that selective evaluation maintains substantial expansion savings across different scaffold constructions for the same task, while also revealing variation in stopping reliability across structures. We have extended Appendix L of the revised manuscript with the six-seed scaffold experiments and corresponding stopping-reliability analyses.
Response to Reviewer WF3A (3/3)
Q3(b). What fraction of complete episode time is spent in the evaluator?
To answer your question about the evaluator's contribution to overall execution time, we examined both the sources of computation cost and the fraction of complete episode time spent on model evaluation.
First, we conducted an independent stage-level profiling experiment across the six BabyAI tasks to identify where computation time is spent. We measured five components: candidate-future generation, input preparation, model decision, environment execution, and other planning/state overhead. The model-decision component includes neural encoding, energy scoring, recursive aggregation, and adaptive control. This breakdown allows us to examine whether the computational savings from selective evaluation primarily arise within the evaluator or from other stages of task execution.
The table reports mean latency per executed step (Full / Ours, ms) from the independent profiling runs.
| Task | Future generation | Input prep | Model decision | Environment | Other |
|---|---|---|---|---|---|
| GoToObj | 2.739 / 2.759 | 0.523 / 0.530 | 13.617 / 10.888 | 0.292 / 0.252 | 0.945 / 0.944 |
| OpenDoor | 8.756 / 8.222 | 0.672 / 0.647 | 15.561 / 8.310 | 0.441 / 0.404 | 1.761 / 1.661 |
| PickupLoc | 3.527 / 3.677 | 0.612 / 0.578 | 16.527 / 14.264 | 0.280 / 0.245 | 0.847 / 0.821 |
| UnblockPickup | 18.423 / 18.202 | 0.790 / 0.794 | 23.978 / 15.334 | 0.465 / 0.437 | 2.682 / 2.561 |
| UnlockPickup | 6.576 / 6.679 | 0.961 / 0.954 | 52.325 / 22.556 | 0.237 / 0.225 | 1.357 / 1.307 |
| BlockedUnlockPickup | 6.762 / 6.730 | 0.971 / 0.969 | 61.297 / 40.874 | 0.235 / 0.212 | 1.530 / 1.522 |
The results show that the main computational savings occur during model decision, while future generation, input preparation, and environment execution remain broadly comparable. For example, on UnlockPickup, model-decision latency decreases from 52.325 to 22.556 ms per step.
To quantify the evaluator's contribution to complete task execution, we separately used evaluator and episode wall times recorded in the same paired-successful closed-loop runs described in Q1. We calculate the evaluator fraction as
The evaluator accounts for 52.02–86.59% of Full's complete episode time, compared with 41.10–81.37% for Ours, with lower fractions across all six tasks. These fractions are calculated directly from the paired episode measurements, while the independent stage-level profiling results explain the sources of computation cost rather than being used to reconstruct the fractions.
Takeaway. The measurements show that model evaluation represents a substantial portion of complete episode execution time, and selective evaluation reduces both its computational cost and its share of overall runtime. Together with the whole-episode speedups reported in Q1, these results clarify how improvements in evaluator efficiency translate into savings during closed-loop task execution. We have added the complete episode timing, evaluator-fraction measurements, and detailed execution-time breakdown to Appendix G of the revised manuscript.
Response to Reviewer WF3A (1/3)
To address your concern about deployment reliability and OOD robustness, we emphasize that our learned radii provide conditional rather than unconditional guarantees. We further examine closed-loop disagreements and the reliability–efficiency trade-off in Q1 and Q2.
We agree that computational savings are limited under zero-shot BossLevel transfer, where Ours expands 32.52 of 34 nodes. However, this is consistent with our adaptive mechanism: when estimated error bounds cannot reliably separate competing actions, the controller expands more subtrees rather than stopping early.
To examine whether task-specific learning can improve efficiency, we trained the model on BossLevel using the same inference mechanism. Expansion reduction increased from 4.34% to 38.63%, while success remained close to Full (74.00% vs. 76.50%). This shows that task-specific training can recover substantial computational savings on complex tasks. We have added these results to Section 4.2 and Appendix E of the revised manuscript.
To answer your questions about runtime savings and the consequences of early-stop disagreements, we conducted three complementary analyses across six BabyAI tasks: complete closed-loop episode timing, paired disagreement–outcome analysis, and first-disagreement action interventions.
To examine whether selective evaluation reduces runtime during complete task execution, we measured episode wall-clock time for Full and Ours on scenarios where both methods succeeded. Both controllers independently executed their low-level policies in closed loop, using saved high-level plans and replans without new LLM API calls. This allows us to compare episode execution time while keeping the high-level planning outputs consistent.
Ours achieves 1.11–1.79× whole-episode speedups across all six tasks. These results show that selective evaluation provides measurable runtime savings during closed-loop execution, beyond the fixed-state decision-latency measurements. We have added the complete episode timing results to Appendix G of the revised manuscript.
To examine whether early-stop disagreements lead to task failures, we analyzed 3,600 paired initial scenarios (six seeds × 100 episodes per task). We identified 808 Ours rollouts with at least one early-certified Full-winner disagreement. Among the 647 corresponding scenarios where Full succeeded, Ours also succeeded in 511 (78.98%).
Disagreements were concentrated in UnlockPickup and BlockedUnlockPickup, accounting for 680 of the 808 affected rollouts (84.2%). The conditional success rates of Ours when Full succeeded were 13.33% (2/15) in UnblockPickup, 52.11% (37/71) in OpenDoor, 86.79% (184/212) in UnlockPickup, and 82.90% (286/345) in BlockedUnlockPickup.
To further investigate whether individual disagreeing actions affect the final outcome, we conducted a first-disagreement intervention. For each affected rollout, we replaced only the first disagreeing action with Full's action at the same state, then resumed Ours for the remainder of the episode. Across the 808 affected rollouts, 73 failures became successes, 25 successes became failures, and 710 outcomes remained unchanged.
Takeaway. These results show that early-stop disagreements do not necessarily lead to task failure, although some disagreements can change the final outcome. The intervention experiment further distinguishes disagreements that affect task completion from those that leave the outcome unchanged. Together with the whole-episode timing results, these analyses provide additional evidence on the reliability–efficiency trade-off during closed-loop execution. We have retained the decision-level reliability analysis in Section 4.4 and added the closed-loop disagreement–outcome and first-action intervention analyses to Appendix F.3 of the revised manuscript.