- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes EmbodiExp to improve embodied task execution by reusing experience from past interactions. The method abstracts local attempts within trajectories into a four-field representation consisting of a subgoal, applicability conditions, an execution policy, and an intended outcome. It extracts effective behaviors and condition-specific avoidance guidance from both successful and failed trajectories. During execution, the system retrieves relevant experiences, checks their applicability, generates actions suited to the current environment, and verifies local outcomes using observable evidence. These outcomes inform task-state updates, enabling the composition of experiences from different sources. The experience bank is constructed before evaluation and subsequently used during evaluation. Experiments on EB-Habitat, EB-ALFRED, and VIGIL demonstrate notable overall improvements.
Critical strengths
- The experience representation has clear execution semantics. The method provides operational guidance, checks applicability conditions, and verifies the outcomes of actual execution. Retaining locally successful experience from failed trajectories is also practically valuable.
- The experimental results are reasonably convincing. Compared with NoExp, success rates increase from 50.0% to 68.0% on EB-Habitat and from 54.7% to 68.3% on EB-ALFRED, while world-state completion on VIGIL improves from 31.6% to 40.8%. The method also outperforms the evaluated memory systems and embodied experience-based methods.
- The paper includes ablations on experience granularity, applicability checking, outcome verification, and the use of failed trajectories. It also reports cross-model experience transfer and both positive and negative transfer. The frozen-bank, three-fold evaluation protocol clearly separates experience construction from evaluation on held-out tasks.
Critical weaknesses
- The incremental contribution over the closest related work remains insufficiently clear. Although the paper compares against WorldMind and EmbodiSkill, it lacks a direct comparison or sufficiently detailed analysis of the methodological differences from skill-based approaches such as MSCE, which incorporate supporting evidence, applicability boundaries, and verification rules.
- The evidence for generalization remains limited in scope. Each of the three environments uses its own experience bank, so results across multiple benchmarks do not establish that a single bank can transfer across environments or action interfaces. Moreover, the EB-Habitat and EB-ALFRED splits are not fully scene-disjoint or task-template-disjoint.
- Comparisons regarding model configurations and compute budgets remain incomplete. The paper specifies the execution backbones but does not clearly identify the models used for experience construction, applicability checking, state maintenance, and outcome verification. In particular, the configurations of the online auxiliary modules in the 8B execution experiments require clarification. The current results therefore do not fully disentangle the contribution of experience reuse from that of additional inference-time computation.
- Negative transfer and the reliability of outcome verification are insufficiently analyzed. On EB-Habitat, 62 episodes that fail under NoExp become successful, but eight previously successful episodes regress to failures. The paper reports this phenomenon without providing specific explanations for the regression cases.
Questions for authors
- Please clarify how EmbodiExp differs from MSCE, WorldMind, and EmbodiSkill in experience representation, applicability conditions, outcome verification, and composition mechanisms. Could you provide a direct comparison with the closest approaches, or compare different experience representations under a shared execution and verification pipeline?
- Could you separately report performance on new combinations of previously encountered subgoals and on unseen subgoals or operation types, together with experience hit rates, applicability-check pass rates, and the proportion of execution performed without experience guidance? Please distinguish cross-task transfer within an environment from cross-environment transfer. If the latter has not been evaluated, the corresponding claims should be qualified.
- Please identify the specific model used for each module, particularly whether all online auxiliary modules in the 8B experiments also use an 8B model or introduce a stronger model. Could you add a NoExp comparison under the same token or model-call budget and separately report online execution and offline construction costs?
3 comments
Weakness 2 & Question 2: Scope and Analysis of Generalization
Scope. We evaluate compositional experience transfer across tasks within each environment, using a separate frozen experience bank for each environment. Transfer of a single bank across environments or action interfaces has not been evaluated. We have clarified this scope in Appendix D.
Cross-Scene and Cross-Task Transfer. Our original three-fold split balances task categories across folds. We have added two separate EB-ALFRED evaluations to assess transfer to unseen scenes and task templates. The scene-disjoint evaluation uses three scene-grouped folds, rebuilding each experience bank after excluding all test-scene trajectories. The task-template-disjoint evaluation uses 300 held-out tasks whose templates are excluded from experience construction. In each setting, NoExp, A-Mem (the strongest baseline in the original EB-ALFRED evaluation) and EmbodiExp are evaluated on the same test tasks. The results are added to Table 9.
| Method | Scene-disjoint SR (%) | Task-template-disjoint SR (%) |
|---|---|---|
| NoExp | 54.3 | 30.7 |
| A-Mem | 59.3 | 36.0 |
| EmbodiExp | 69.0 | 62.3 |
EmbodiExp outperforms A-Mem by 9.7 percentage points on unseen scenes and 26.3 percentage points on unseen task templates, supporting both cross-scene and cross-task experience transfer within EB-ALFRED.
Subgoal Generalization and Experience Use. We conducted a separate supplementary evaluation on 300 EB-Habitat episodes, matching tasks, folds, and initial observations between NoExp and EmbodiExp. This supplementary run achieved overall SRs of 50.0% and 70.0% for NoExp and EmbodiExp, respectively. Within each fold, tasks are grouped by whether their individual subgoals and complete goal configurations appear in the source tasks referenced by its experience bank. Grounded subgoals distinguish the goal condition, object category, and target location.
| Task group | Episodes | NoExp SR (%) | EmbodiExp SR (%) | Hit-rate bounds (%) | Applicability pass (%) | Actions without guidance (%) |
|---|---|---|---|---|---|---|
| Seen subgoals, new combinations | 65 | 52.3 | 72.3 | 57.4–66.2 | 96.5 | 40.1 |
| Unseen grounded subgoals | 144 | 46.5 | 66.7 | 56.0–65.5 | 96.7 | 41.7 |
| Seen subgoals, seen combinations | 91 | 53.8 | 73.6 | 36.4–43.4 | 96.2 | 56.5 |
Hit-rate bounds reflect incomplete relevance logging: selector-confirmed relevant retrievals (lower) and nonempty retrievals (upper), each divided by all queries. Applicability and unguided-action rates use checked candidates and submitted environment actions, respectively.
Gains persist on new goal configurations: improvements are comparable for new and seen combinations (+20.0/+19.8 pp), while tasks containing unseen grounded subgoals improve from 46.5% to 66.7%.
Unseen Operation Types. Unseen grounded subgoals can involve familiar operations applied to new object categories or target locations. The analysis above supports transfer to new grounded goals and goal combinations, but does not establish transfer to previously unseen operation types.
Weakness 3 & Question 3: Model Configurations and Compute
Model Configurations. The main experiments use Qwen3.6-35B-A3B on EmbodiedBench and Qwen3.6-27B on VIGIL for experience construction and all online LLM modules. In Figure 4A, the constructor (Qwen3.6-35B-A3B or GPT-5.4) operates exclusively offline, while the selected executor handles all online operations, including applicability checking, Task State maintenance, and outcome verification. All online modules in the 8B experiments use Qwen3-VL-8B. These configurations are specified in Appendix B.
Contribution of Experience Reuse. We added an empty-bank control on EB-Habitat that retains the same executor, action limits, and Task State, outcome-verification, and replanning prompts as EmbodiExp. Revised Table 8 reports success rates and average online costs per episode.
| Method | SR (%) ↑ | Env. steps | Model calls | Tokens (k) |
|---|---|---|---|---|
| NoExp | 50.0 | 15.96 | 7.34 | 37.84 |
| EmbodiExp (empty bank) | 50.7 | 16.02 | 21.78 | 74.56 |
| EmbodiExp (Ours) | 68.0 | 13.67 | 17.44 | 77.22 |
The empty-bank control achieves 50.7% SR, close to NoExp’s 50.0%, despite using 96.6% of EmbodiExp’s tokens and making more model calls. Adding the experience bank improves SR by 17.3 percentage points with comparable token usage and fewer calls, supporting the contribution of experience reuse beyond additional online computation.
Offline Costs. On EB-Habitat, source-trajectory collection and experience-bank construction together require 2,187 model calls and 10.87M tokens in total across the three folds. These costs include collecting the 300 shared source trajectories and constructing the fold-specific experience banks, each using 200 source trajectories. Local MiniLM indexing adds no generative-model calls or tokens. These offline costs are reported separately from online execution costs in Appendix C.2.
Weakness 4: Negative Transfer and Outcome Verification
Negative Transfer. We analyzed the eight episodes that succeed under NoExp but fail under EmbodiExp and added the observed failure modes to Section 4.3.
| Failure mode | Cases |
|---|---|
| Budget exhaustion during search or repeated attempts | 3 |
| Manipulation of non-target objects | 3 |
| Violation of global task constraints | 1 |
| Execution deviating from the selected policy | 1 |
Outcome Verification. We reviewed 1,121 recorded verification decisions against the corresponding action and environment-feedback logs, checking whether the task’s required target satisfied the subgoal at the time of each decision.
| Verifier decision | Checks | Review result |
|---|---|---|
| Subgoal completed | 359 | 357 supported by evidence; 2 incorrect (0.56%) |
| Completion not confirmed | 759 | No missed completions identified in the recorded evidence |
| Unknown | 3 | No action had been executed |
We thank the reviewer for the constructive feedback. We have revised the manuscript and uploaded the updated version.
Weakness 1 & Question 1: Comparison with MSCE, WorldMind and EmbodiSkill
Direct Comparison. We have added MSCE to the baselines in Table 1, with its adaptation to our frozen-bank protocol detailed in Appendix B.6. EmbodiExp outperforms MSCE, WorldMind, and EmbodiSkill on EB-Habitat and EB-ALFRED.
Methodological Differences. We have expanded the Experience and Skill Learning paragraph in Related Work to clarify the methodological distinctions. MSCE promotes evidence-supported policies into callable skills with applicability boundaries and verification rules. WorldMind learns causal rules from prediction errors and planning heuristics from successful trajectories. EmbodiSkill selectively revises persistent procedural skills by distinguishing skill defects from execution lapses.
EmbodiExp constructs subgoal experiences through local outcome attribution, whereas MSCE uses reflection-weighted propagation of terminal feedback to govern skill promotion. During reuse, newly verified outcomes can establish the conditions for applying experiences from other tasks, enabling online composition.