- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
The paper introduces HPEM, an external memory that stores reusable processes and workflows with shared subprocess identities. Evidence from interactions determines retrieval eligibility, and memory is frozen before evaluation.
Critical strengths
- The method produces clear success gains on WebShop and ALFWorld.
- Reusing the same memory across model sizes is useful, and the paired evaluations and frozen-memory checks strengthen the results.
Critical weaknesses
-
The main concern is whether the gains come from hierarchical experience memory or the authored process templates. A fixed-template baseline is missing.
-
The structural comparisons are mixed: Full improves strict success over Flat, but Flat achieves higher reward at lower cost. The shared-identity ablation needs more implementation detail, while the composition ablation’s confidence interval includes zero.
-
The feedback ablation changes both memory construction and retrieval coverage, leaving the source of its benefit unclear. Transfer is mostly tested on new instances of familiar task families, and the AndroidWorld gain is uncertain.
Questions for authors
-
How does HPEM compare with the same templates without experience acquisition?
-
What changes in the shared-identity ablation besides node sharing?
-
Can downstream failures lower trust once local evidence takes priority?