- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces SEA-Mem for recovering complementary evidence from long dialogue histories under a limited source budget. It combines query-guided source addressing, one-hop associative completion, and LLM-based source selection while retaining original turns as answer evidence. Experiments on LongMemEval and LoCoMo examine answer quality, interference robustness, efficiency, and component contributions.
Critical strengths
- The paper addresses a meaningful problem of retaining complementary evidence when semantically similar memories compete for limited context. Distinguishing candidate evidence recovery from final evidence retention provides a useful perspective on dialogue memory.
- SEA-Mem maintains clear source provenance throughout retrieval and selection. Using associations to guide access while presenting original turns to the answerer makes the evidence pathway traceable.
- The evaluation covers two benchmarks and two backbones, with controlled interference experiments and component ablations. Freezing memory construction across interference conditions helps examine retrieval behavior separately from writing-stage changes.
Critical weaknesses
- The motivation for retaining complementary evidence under a limited source budget is clear, but SEA-Mem’s technical advance over existing associative memory methods remains insufficiently established. The paper should identify its distinctive design and explain which limitation of prior methods it addresses.
- In Section 4.2, SEA-Mem uses CA1-Select, whereas Dense-native and AssoMem-native directly return their top-k sources. Although the component ablations are informative, the advantage over these baselines with the same selector remains unclear.
- The aggregate and category-level results in Tables 1 and 4 are inconsistent. These discrepancies make the reported performance and robustness to history expansion difficult to verify.
- The interference experiments provide useful evidence, but the accuracy–token trade-off remains unclear. Section 4.2 varies the number of sources rather than the token budget, while Table 7 reports token usage separately, leaving it unclear how much context SEA-Mem can save without sacrificing accuracy and when its advantage diminishes as more context is allowed.
Questions for authors
- What is SEA-Mem’s principal technical distinction from the associative-memory approaches discussed in the paper, such as AssoMem, HippoRAG-2, and A-MEM? Please clarify which limitation these approaches have that SEA-Mem addresses, and what evidence demonstrates the benefit of its distinctive design. (refer to Weakness 1)
- Does SEA-Mem retain its advantage when Dense and AssoMem candidates are processed by the same CA1 selector, with comparable candidate budgets and the same final source limit? (refer to Weakness 2)
- Can you reconcile the aggregate and category-level results in Tables 1 and 4? For example, weighting SEA-Mem’s DeepSeek Oracle category scores by the standard category counts gives approximately 82.1%, whereas Table 1(a) reports 79.4%. (refer to weakness 3)
- Could you compare SEA-Mem and the baselines across matched Reader token budgets, including larger budgets, and report accuracy, distractor occupancy, and total query-time LLM tokens on the same examples? LLMs are capable of processing large numbers of tokens. Reducing the input from, for example, 8K to 4K tokens alone does not demonstrate that the retained memories better support answering. Please clarify what information SEA-Mem removes and whether its benefit comes from eliminating confusable or irrelevant memories while preserving necessary evidence, or from another mechanism.
4 comments
To Reviewer 7q4Z — Part 2/2
W3&Q3. Experimental data reconcile the aggregate
Thank you for bringing this discrepancy to our attention. We identified an error in the original aggregation and recomputed the scores from the question-level results using the evaluation protocol described in the manuscript.
-
Table 1. SEA-Mem’s overall DeepSeek accuracy on LongMemEval-Oracle remains 79.4% (397/500). The corrected category scores in Table 1(b), in column order, are 64/78 (82.1%), 67/70 (95.7%), 23/30 (76.7%), 50/56 (89.3%), 105/133 (78.9%), and 88/133 (66.2%). These counts sum to 397 correct answers across 500 questions, matching Table 1(a).
-
Table 5 (Table 4 in the original submission). The only error in this table was HippoRAG-2’s overall F1. We corrected it from 40.0% to 38.6% in both Tables 1(a) and 5. All category-level F1 scores were correct.
Q4. Accuracy-Efficiency Trade-off across Matched Token Budgets
To test if SEA-Mem’s advantage persists across growing Reader budgets, we compared SEA-Mem, AssoMem, and Dense on same LongMemEval-S questions (Semantic-50 interference). We applied four matched evidence caps (256 to 4,096 tokens) while keeping all candidate pools fixed (SEA-Mem retained its full native pool); only CA1 was adapted, replacing the five-turn limit with a token cap to select a sufficient, nonredundant set without forced filling or designated core turns. Keeping native rankings for baselines, all methods used identical packing rules, Reader, and Judge to report accuracy, distractor occupancy, and estimated query-time LLM tokens.
| Reader evidence cap | Method | Judged accuracy ↑ | Distractor occupancy ↓ | Query-time LLM tokens/question ↓ |
|---|---|---|---|---|
| 256 | SEA-Mem | 72.7% | 1.5% | 1,364 |
| AssoMem | 56.7% | 25.2% | 328 | |
| Dense | 49.3% | 32.7% | 327 | |
| 512 | SEA-Mem | 77.3% | 2.2% | 1,511 |
| AssoMem | 66.0% | 31.0% | 525 | |
| Dense | 62.7% | 35.3% | 523 | |
| 1,024 | SEA-Mem | 80.0% | 2.2% | 1,776 |
| AssoMem | 71.3% | 32.3% | 915 | |
| Dense | 69.3% | 37.6% | 911 | |
| 4,096 | SEA-Mem | 80.0% | 2.3% | 1,778 |
| AssoMem | 78.7% | 52.6% | 3,228 | |
| Dense | 77.3% | 61.7% | 3,170 |
Across all 150 Semantic-50 questions, SEA-Mem kept distractor occupancy low even at the 4,096-token budget: 2.3% for SEA-Mem, compared with 52.6% for AssoMem and 61.7% for Dense. We found that SEA-Mem primarily filters out topically similar memories about different entities or occurrences. For example, it excluded advice about the Fitbit Inspire HR while retaining the user’s Charge 3 updates. It also excluded a weekend trip with friends while retaining the account of the user’s week-long family trip to Hawaii.
Thank you for your rebuttal. My main concerns are addressed, and errors are corrected; thus, I update my rating to 3: weak acceptance.
Thank you for your careful review and for raising your rating. Your feedback helped us clarify the technical distinctions, strengthen the controlled comparisons, and improve the accuracy of our reported results.
To Reviewer 7q4Z — Part 1/2
We are grateful for your time and effort in reviewing our work. To address your questions, we clarified SEA-Mem's distinction from prior methods, tested retrieval with a shared CA1 selector, corrected score discrepancies, and compared accuracy, distractor occupancy, and token costs across matched Reader budgets.
SEA-Mem's key distinction is combining event discrimination with evidence recovery: it isolates the target episode using query-specific cues, follows associations to recover complementary details, and selects a compact set of original turns that jointly support the answer.
To isolate whether SEA-Mem's advantage stems from its selector or its retrieval mechanism, we use the same LongMemEval-S questions. Dense and AssoMem match SEA-Mem’s candidate count using their top-ranked turns. We compare Native readout (top 5 turns directly to the Reader) against Shared CA1 (applying SEA-Mem’s CA1 selector to each candidate pool to select up to 5 turns). Results:
Adding CA1-Select can improve accuracy in other method, however, DG-Address and CA3-Complete jointly improve accuracy beyond CA1-Select alone.