- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
To address the issue of premature memory compression in long-context streaming inference—which can lead to the loss of potentially critical evidence—this paper proposes CoEM. Within a fixed memory budget, CoEM maintains both committed facts and pending raw text segments. It employs reinforcement learning to decide whether to retain, commit, or discard pieces of evidence, while utilizing a frozen natural language inference (NLI) verifier to check the source support for any facts proposed for commitment. The core contribution lies in integrating raw text buffering, deferred commitment, and source verification into a recurrent memory management framework, supported by a training strategy that combines final-answer rewards with step-level evidence feedback. The authors evaluate the method using Qwen3.5-4B and Qwen3.5-9B models across three multi-hop question-answering benchmarks and document streams of varying lengths. The results demonstrate that CoEM outperforms memory-based baselines with equivalent budget constraints; specifically, the 9B model achieves an improvement of 10.4–11.4 F1 points when processing a stream of 6,400 documents. Furthermore, ablation studies, evidence-interval testing, and verifier-based audits provide a detailed analysis of the roles and limitations of each component.
Critical strengths
The paper proposes a reasonable and feasible memory mechanism designed to address critical failure modes. Within a fixed memory budget, CoEM retains segments of the original text whose utility is not yet clear, allowing this information to inform subsequent decision-making. Furthermore, it employs source verification to mitigate the risk of incorporating unsupported facts into memory. This design directly tackles the issue where the significance of certain evidence only becomes apparent later—after the original details have already been compressed or lost—which is the primary reason I find the technical approach valuable.
The performance improvements are consistent, and the key findings are well-supported by experimental evidence. Across two model scales, three multi-hop question-answering benchmarks, and various input lengths, CoEM consistently outperforms the memory-based baselines (which are matched for budget). Notably, the 9B model achieves an improvement of 10.4–11.4 F1 points on the longest input sequences. The inclusion of statistics from three different random seeds, paired confidence intervals, and additional comparisons against the original ReMemR1 further bolsters the credibility of these results. This evidence confirms the system's practical effectiveness for the tasks evaluated and serves as a significant positive factor in the overall assessment.
Critical weaknesses
The independent contribution of the core mechanism has not been sufficiently validated. While the paper emphasizes "learning when to commit," the ablation study—which removes the pending set—simultaneously alters the retention method and the allocation of the memory budget. Furthermore, a fixed two-step delay is inadequate as a representative baseline for competitive commitment strategies. Consequently, it is difficult to discern whether performance gains stem from learning the optimal timing for commitment or simply from retaining a larger volume of uncompressed information. The absence of comparisons against strong extractive caching baselines—under equivalent budget and validator constraints—as well as the lack of comparisons with well-tuned waiting strategies, leaves the necessity and incremental value of the core innovation unclear.
The evaluation fails to adequately address the critical challenge of capacity competition. Each dataset is assessed using only 128 questions, with the full supporting text capped at 4,096 tokens and distractor passages truncated to 96–128 tokens. Increasing the input length primarily serves to increase the volume of distractors, without simultaneously testing the system’s ability to handle a greater total amount of supporting information or more complex chains of reasoning. Moreover, while the stress tests involving dense source evidence report capacity-related events and discard rates, they fail to provide the corresponding answer accuracy. As a result, the current evidence is insufficient to determine whether CoEM can maintain its advantage when a large body of relevant evidence—or multiple concurrent, pending reasoning chains—compete for limited memory. This limits both the scope of the core conclusions and their overall persuasiveness.
Questions for authors
Given identical memory budgets, verifiers, and training conditions, what performance gains can be achieved by learning the timing of "commit" actions, as opposed to using robust extractive caching or a tuned waiting strategy?
As the amount of supporting evidence increases—and multiple pending chains of reasoning compete for limited memory—how do the Answer F1 score and the loss rate of critical evidence for CoEM evolve? Does the model maintain its advantage relative to the baseline?
5 comments
Response to Reviewer AyfX (2/4): W1 & Q1 (continued)
Table R10. Learned timing against extractive caching, tuned waiting strategies, and reference variants (Qwen3.5-4B). Revised Table 2 and new Table 18 in Appendix F.5.
| Variant (answer F1) | HotpotQA 800 | 2Wiki 800 | HotpotQA 6,400 | Pending tokens |
|---|---|---|---|---|
| Component ablation (Table 2) | ||||
| Eager + verifier ( = 0) | 77.2 | 66.0 | 70.6 | 0 |
| Verbatim-retention alternatives | ||||
| ReMemR1† + verbatim buffer | 82.1 | 71.9 | 76.0 | 251 |
| Robust extractive cache | 81.8 | 71.6 | 76.9 | 247 |
| Matched timing controls (waiting strategies) | ||||
| Fixed two-chunk delay + matched retry | 82.8 | 72.8 | 79.2 | 203 |
| Tuned delay (4 chunks) + matched retry | 83.0 | 73.1 | 79.6 | 221 |
| Entity-triggered wait + matched retry | 83.2 | 73.4 | 80.1 | 196 |
| CoEM (learned timing) | 85.5 | 76.1 | 84.2 | 138 |
Pending tokens is the mean occupancy of verbatim text at 6,400 documents on HotpotQA. The extractive cache and the waiting strategies use the same budget split, verifier, and RL training as CoEM. ReMemR1† + verbatim buffer keeps the unverified memory updates of ReMemR1†.
Answer to Q1.
-
Against robust extractive caching, learning commitment timing gains 3.7 / 4.5 points (HotpotQA / 2WikiMultiHopQA, 800 documents) and 7.3 points at 6,400 documents.
-
Against the best tuned waiting strategy, it gains 2.3 / 2.7 points at 800 documents and 4.1 points at 6,400 documents.
-
The gains do not come from keeping more uncompressed text. At 6,400 documents, the pending set of CoEM holds 138 tokens on average, fewer than the extractive cache (247) and the best waiting strategy (196).
Why learned timing helps. Table R11 tracks supporting evidence in the source-to-bridge gap intervention, where 32 or 128 chunks separate a source excerpt from the passage that links it to the question.
Table R11. Retention and commitment timing of supporting evidence (Qwen3.5-4B, HotpotQA, 6,400 documents). New Table 19 in Appendix F.5.
| Variant | Supporting excerpts still verbatim when the bridge arrives (gap 128) | Committed at the bridge step or the next step (gap 32) |
|---|---|---|
| Robust extractive cache | 52.7% | 23.8% |
| Fixed two-chunk delay + matched retry | 18.6% | 6.1% |
| Tuned delay + matched retry | 27.9% | 10.4% |
| Entity-triggered wait + matched retry | 71.2% | 54.6% |
| CoEM | 89.8% | 81.3% |
The extractive cache scores evidence by its similarity to the question, but delayed evidence has low similarity when it arrives, so about half of it is evicted before the bridge. Fixed delays promote supporting excerpts long before the bridge and compress them while their relevance is unclear. The entity trigger misses links through aliases. CoEM keeps 89.8% of supporting excerpts until the bridge and commits 81.3% of them at the bridge step or the next step. It therefore compresses evidence close to the moment when later context makes its role clear, which is what a fixed rule cannot do.
Effect of the budget split. We also retrained all memory agents at total budgets of 512, 1,024, and 2,048 tokens. CoEM leads at every budget, and CoEM with 512 tokens (80.1 / 69.4) exceeds every baseline with 2,048 tokens (best 78.9 / 68.5). This further shows that the advantage of CoEM does not come from a larger amount of retained memory.
Revision. Table 2 adds the matched controls, Section 4.4 limits the claim to the matched comparisons, and Appendices F.4 and F.5 give the details.
Response to Reviewer AyfX (3/4): W2 & Q2
W2 & Q2. More supporting evidence and multiple pending reasoning chains competing for limited memory
Reviewer AyfX, Weakness 2
The evaluation fails to adequately address the critical challenge of capacity competition. Each dataset is assessed using only 128 questions, with the full supporting text capped at 4,096 tokens and distractor passages truncated to 96–128 tokens. Increasing the input length primarily serves to increase the volume of distractors, without simultaneously testing the system’s ability to handle a greater total amount of supporting information or more complex chains of reasoning. Moreover, while the stress tests involving dense source evidence report capacity-related events and discard rates, they fail to provide the corresponding answer accuracy. As a result, the current evidence is insufficient to determine whether CoEM can maintain its advantage when a large body of relevant evidence—or multiple concurrent, pending reasoning chains—compete for limited memory. This limits both the scope of the core conclusions and their overall persuasiveness.
Reviewer AyfX, Question 2
As the amount of supporting evidence increases—and multiple pending chains of reasoning compete for limited memory—how do the Answer F1 score and the loss rate of critical evidence for CoEM evolve? Does the model maintain its advantage relative to the baseline?
Response.
Our evaluation protocol is as follows. Each dataset has 128 questions, the full supporting text is at most 4,096 tokens, and each distractor is the longest complete-sentence prefix of 96 to 128 tokens. We follow the protocol of ReMemR1 so that results are directly comparable with prior work. It also guarantees that the full-context baseline sees all supporting text, and it makes each shorter context a subsequence of every longer one, which allows paired comparisons across lengths. We agree that under this protocol a longer input mainly adds distractors. We therefore added the following tests with Qwen3.5-4B at 6,400 documents.
We measure the loss rate of critical evidence as the share of annotated supporting relations, already observed when the last chunk has been read, that cannot be recovered from the retained text. For CoEM it is measured before final resolution.
(1) Answer F1 under pending-set stress. Our stress test reported capacity events and forced drops under three orderings of the 2WikiMultiHopQA stream: the ordinary ordering of the main evaluation, a gap of 128 chunks between each source excerpt and its bridge evidence, and a source-dense ordering that places many unresolved source excerpts close together so that they compete for the pending set at once. Table R12 adds answer F1 and the loss rate of critical evidence.
Table R12. Answer F1 under pending-set stress (Qwen3.5-4B, 2WikiMultiHopQA, 6,400 documents). New Table 20 in Appendix F.6.
| Condition | MemAgent | GRU-Mem | ReMemR1† | CoEM | CoEM forced drops | Critical-evidence loss: CoEM / best baseline |
|---|---|---|---|---|---|---|
| Ordinary ordering | 54.6 | 61.1 | 64.4 | 73.9 | 0.5% | 15.1% / 33.6% |
| Gap of 128 chunks | 37.8 | 41.9 | 43.0 | 65.6 | 1.8% | 19.6% / 52.3% |
| Source-dense stress | 46.1 | 52.3 | 55.4 | 66.9 | 7.6% | 23.7% / 44.0% |
Response to Reviewer AyfX (1/4): W1 & Q1
Thank you for the careful review and for recognizing the soundness of the mechanism and the consistency of the gains. Both of your questions ask for tests of the core mechanism under equal conditions, and we added the controls and stress tests below. Because the discussion period is short, all new experiments use Qwen3.5-4B, and there was not enough time to repeat them with Qwen3.5-9B. All changes are marked in red in the revised PDF.
W1 & Q1. Gains from learning commitment timing under identical budgets, verifiers, and training
Response.
We agree that two controls were missing. The eager variants were designed as ablations inside the CoEM controller. They remove the pending set and give its 256 tokens to committed memory (BP = 0, BM = 1,024), so that the total budget stays at 1,024 tokens. This keeps the comparison budget-matched, but, as you point out, it changes the retention method and the budget split at the same time. The fixed two-chunk delay was meant as the simplest timing rule, not as a tuned waiting strategy. To separate learned timing from these choices, we added the following controls. The extractive cache and the waiting strategies use the same budget split as CoEM (BP = 256, BM = 768), the same frozen verifier (η = 0.90), and the same RL training with Qwen3.5-4B. The cache changes how verbatim evidence is retained, and the waiting strategies change only when promotion is first attempted.
Robust extractive cache. At every chunk, source sentences are rescored by their similarity (BGE-M3) to the question and to committed memory. The highest-scoring sentences are kept within 256 tokens and the lowest-scoring ones are evicted. The policy writes facts from the cache and the current chunk through the same verifier.
Tuned waiting strategies. These keep the retention, retry, and capacity rules of CoEM and fix only when promotion is first attempted. We use a fixed delay tuned on the development set over 1, 2, 4, and 8 chunks (selected: 4 chunks), and an entity-triggered wait that attempts promotion when the current chunk mentions an entity that also appears in the pending excerpt. After this first attempt, each policy makes its own KEEP, retry, and DROP decisions under the same limits as CoEM.
Reference variants. We also include ReMemR1† with a 256-token verbatim buffer, which keeps the unverified memory updates of ReMemR1†, the two-chunk delay with matched retry, and the eager variant of Table 2, which has no pending set.