- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes ElasticMem, a latent memory framework that jointly learns memory retrieval and adaptive token-budget allocation through GRPO, achieving promising results on memory QA and embodied agent tasks.
Critical strengths
- Treating memory allocation as a learnable resource is a meaningful direction for memory-augmented agents and it is significant in industrial deployment.
- The method achieves consistent improvements across memory QA and embodied agent tasks with multiple backbone sizes.
Critical weaknesses
- The budget policy is optimized without an explicit token-cost penalty. It remains unclear whether elastic allocation outperforms fixed allocation under matched token budgets.
- There exists a concern of PersonaMem-128K, because a case study of it contains two identical answer options (Tab.41 (b) (c)).
Questions for authors
- Can the authors provide accuracy–token trade-off comparisons between elastic and fixed allocation under matched token budgets?
- The proposed budget policy combines memory selection and capacity allocation, but their individual contributions are not clearly disentangled. Can the authors provide a binary gating baseline that either discards a memory or assigns it a fixed budget would help determine whether fine-grained elastic allocation is truly necessary.
4 comments
Response 2
Continuation of our response to [W1, Q1] from the previous page:
At , both datasets use fewer tokens and accuracy changes by at most 0.2 percentage points. At , total token use falls by 8.3% on LoCoMo and 5.6% on PersonaMem-128K, with accuracy losses of 1.0 and 0.8 percentage points, respectively. Thus, the learned allocator improves accuracy when the per-question budget is fixed, and an explicit penalty provides a separate way to trade accuracy for lower token use when the budget can vary.
W2: Potential issue with PersonaMem-128K answer options.
Response. Thank you for pointing out the duplicated option. We checked the prompt used in the Mem0 evaluation: option (b) describes a deeper appreciation for yoga, while option (c) describes a stronger interest in meditation with unchanged feelings toward yoga. When transcribing the case study for the original Table 41, we inadvertently repeated (b) in place of (c). We have corrected (c) wherever this question appears in Appendix I.2 of the revised manuscript (Tables 42–44 and 46). The gold answer and Mem0’s reported prediction are both (b).
Q2: Disentangling memory selection and capacity allocation.
Response. Thank you for suggesting a binary gating baseline. At the same injected-memory budget for every question, Full ElasticMem achieves 79.9% weighted QA accuracy versus 76.1% for Binary Gating, a gain of 3.8 percentage points. We report this comparison in §4.3 and give the full protocol and results in Appendix J, Table 72.
Setting. We evaluate Qwen2.5-7B-Instruct on four QA benchmarks. All variants use the same memory-bank construction, retrieval count, projector architecture, training data, and GRPO protocol. During both training and evaluation, each variant injects exactly 80 latent memory tokens per PersonaMem-32K question and 160 per question on each of the other three benchmarks.
- Uniform retains all retrieved chunks and divides the budget as evenly as possible. Allocations differ by at most one token.
- Binary Gating assigns either 0 or 20 tokens to each chunk. It learns which four chunks to retain at a budget of 80, or which eight to retain at a budget of 160.
- Elastic w/o Gating retains every chunk and learns an allocation of 1–20 tokens per chunk.
- Full ElasticMem learns an allocation of 0–20 tokens per chunk, so it can both discard chunks and vary the capacity of those retained.
Both elastic variants allocate tokens in retrieval order. At each step, we mask allocations that would leave too few or too many tokens for the remaining chunks. The last chunk receives exactly the remainder.
Table 3. Mean QA accuracy across five independent training seeds at matched per-question budgets (Appendix J, manuscript Table 72). The weighted average uses 50, 233, 314, and 100 test questions, respectively (Appendix A.1).
| Dataset | Tokens per question | Uniform | Binary Gating | Elastic w/o Gating | Full ElasticMem |
|---|---|---|---|---|---|
| PersonaMem-32K | 80 | 0.836 | 0.852 | 0.864 | 0.876 |
| PersonaMem-128K | 160 | 0.749 | 0.767 | 0.778 | 0.799 |
| LoCoMo | 160 | 0.757 | 0.774 | 0.801 | 0.814 |
| LongMemEval | 160 | 0.640 | 0.662 | 0.700 | 0.716 |
| Weighted Avg. | — | 0.743 | 0.761 | 0.783 | 0.799 |
Results. Binary Gating improves on Uniform by 1.8 percentage points in weighted accuracy (0.743 to 0.761). When every retrieved chunk is retained, learning its token budget raises weighted accuracy from 0.743 (Uniform) to 0.783 (Elastic w/o Gating). Allowing zero-token allocations as well raises it to 0.799, a further 1.6 points.
Full ElasticMem outperforms Binary Gating by 2.4, 3.2, 4.0, and 5.4 percentage points across the four benchmarks, respectively. Thus a learned keep-or-discard rule is useful, and learning how much capacity to assign to retained chunks improves accuracy further under the same token budget.
We would like to thank the reviewer once again for their valuable time and thoughtful feedback. We sincerely hope that our responses and revisions have adequately addressed the concerns raised and further improved the clarity and overall quality of the manuscript. We would greatly appreciate the reviewer's further assessment of these improvements and warmly welcome any additional feedback or discussion.
Thank you for the detailed response and additional experiments. The new results have largely addressed my main concerns. I appreciate the authors' efforts and will maintain my positive rating.
Thanks for the Reviewer’s Constructive Feedback
Thank you for your thoughtful and constructive feedback. We are pleased to hear that our responses have addressed all of your concerns. We are committed to incorporating the suggested changes in our revisions to further enhance the manuscript.
Response 1
We sincerely thank the reviewer for their thoughtful feedback and constructive suggestions. We appreciate the concerns regarding token-budget fairness, the necessity of fine-grained allocation, and benchmark quality. Below, we address each point in detail.
Response. Thank you for raising this question. The default ElasticMem reward in §3.6, Eq. (17) has no explicit token-cost penalty. We added two experiments with Qwen2.5-7B-Instruct. First, elastic allocation outperforms uniform allocation in all 16 comparisons when both methods receive exactly the same memory-token budget on every question. Second, when the budget can vary, adding a token-cost penalty reduces token use with a measurable accuracy trade-off. We summarize both results in §4.3 and report the full comparisons in Appendix J, Tables 70 and 71.
(i) Accuracy under an exact per-question memory budget. For each question, both methods receive the same Z retrieved chunks and inject exactly B=kZ latent memory tokens, where k∈{4,8,12,16}. We train each method under its assigned constraint and enforce that same constraint at evaluation.
Fixed (uniform) allocation assigns exactly k tokens to each of the Z chunks, so the total is kZ=B.
Elastic allocation uses a feasibility mask in retrieval order during both training and evaluation. Before allocating tokens to chunk j, let Rj=B−∑i<jbi be the remaining budget and m=Z−j the number of chunks still to follow. The policy can choose only integer allocations satisfying
max(1,Rj−20m)≤bj≤min(20,Rj−m).
This leaves enough tokens to give each remaining chunk at least one, while ensuring that the remaining chunks can absorb the balance at no more than 20 tokens each. At the last chunk, m=0, so the only feasible choice is bZ=RZ. Both methods therefore retain every retrieved chunk and use exactly B injected tokens on every question. For example, on LoCoMo with Z=20 and B=160, uniform allocation gives every chunk eight tokens, while elastic allocation can distribute those same 160 tokens unevenly.
Table 1. QA accuracy under matched per-question memory budgets (Appendix J, manuscript Table 70).
Elastic allocation improves accuracy by 1.6–6.6 percentage points across the four datasets and four budgets. At exactly 240 injected tokens per question, it gains 4.6 points on LoCoMo and 6.6 points on LongMemEval. Because both methods retain the same chunks and inject the same number of tokens, these comparisons show that learning how to distribute a fixed memory budget improves accuracy over dividing it evenly.
(ii) Effect of an explicit token-cost penalty. On LoCoMo and PersonaMem-128K, we also allow the injected memory length to vary by question and train with the reward
Rλ=Racc−λZBmax∑j=1Zbj.
We vary only λ, with λ=0 recovering the original QA reward. The penalty applies to injected memory tokens as a fraction of the available latent capacity. The table reports mean total tokens per question, including task input, injected memory, and generated output, following the accounting in manuscript Table 2.
Table 2. QA accuracy and mean total tokens per question as the token-cost penalty varies (Appendix J, manuscript Table 71).