- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
S1: Using retrieval feedback to repair graph memory, rather than keeping the graph fixed after construction, is a well-motivated idea. S2: The method outperforms 16 baselines on four benchmarks, and the learned policies transfer to GraphRAG and LightRAG graphs and to other backbones without retraining.
Critical strengths
S1: Using retrieval feedback to repair graph memory, rather than keeping the graph fixed after construction, is a well-motivated idea. S2: The method outperforms 16 baselines on four benchmarks, and the learned policies transfer to GraphRAG and LightRAG graphs and to other backbones without retraining.
Critical weaknesses
W1: The novelty is limited. Repairing graph links from feedback has been explored by FluxMem [1], which the paper identifies as the closest work but does not compare against. The three edit operations also resemble the add and update operations already learned by RL-based memory managers such as Memory-R1[2]. W2: The main results do not test the claimed continual evolution. W3: The extractor already identifies the evidence passages among the top 25 results, so the gain may come from this selection rather than from editing the graph.
[1] FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding [2] Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Questions for authors
Refer to Weakness.
5 comments
Response to Reviewer SiQX [Part 2]
2. The Continual Evolution Experiment
Your Concern (W2): The main results do not test the claimed continual evolution.
Thanks for raising this point. We would like to clarify that the main results adopt the per-query setting by design, while the continual setting is evaluated separately in Appendix C.3 (Table 7, Page 22). The reason is fairness: deciding whether a repair should stay in the graph requires retrieval feedback, and if this feedback came from the labels of the evaluation set, G-Evolver would receive supervision that none of the baselines has. The per-query setting therefore measures what a single repair brings without any such feedback, and Table 7 tests the full continual mode. We summarize this experiment below and extend it to show how performance develops along the query stream.
(1) Continual Evolution in Table 7. The queries of each conversation in LoCoMo and PersonaMem are randomly split into two halves. The first half simulates past interactions: its queries arrive in sequence, and the repair produced for each of them is written into the graph only if it passes the consolidation rule, using either the first-half labels with Eq. (5) or its label-free form judged by GPT-5-mini (Appendix C.3), where the neighbors checked are only the previously served queries. The second half simulates future interactions: it is evaluated on the graph accumulated from the first half, still with its own per-query repairs, and its labels are never used. The numbers in parentheses are gains over the per-query setting of the main results.
| Per-query (main results) | Continual (GPT-5-mini verification) | Continual (gold-label verification) | |
|---|---|---|---|
| LoCoMo F1 | 37.48 | 38.43 (+0.95) | 39.89 (+2.41) |
| LoCoMo Judge | 58.02 | 59.49 (+1.47) | 62.32 (+4.30) |
| PersonaMem-32K ACC | 58.74 | 59.59 (+0.85) | 62.31 (+3.57) |
| PersonaMem-128K ACC | 49.17 | 49.91 (+0.74) | 52.00 (+2.83) |
| Avg. Δ over HippoRAG2 | +5.80 | +6.67 | +8.78 |
Since the second half never contributes labels, these gains come from repairs consolidated for earlier queries that carry over to later ones, which is exactly what continual evolution claims. The gains hold on all four metrics even when consolidation is verified by GPT-5-mini instead of gold labels, so continual evolution does not depend on annotated feedback. This also means the main results are a conservative estimate of G-Evolver.
(2) Performance along the Query Stream. Table 7 reports only the final state after consolidation. To examine how performance develops as repairs accumulate, we replay the same protocol conversation by conversation on LoCoMo (10 conversations) and PersonaMem-32K (37 conversations) in their original order, and evaluate the full query set after every 10% of the conversations are processed. Conversations not yet processed are answered by plain retrieval on their initial graphs, so 0% corresponds to the unrepaired graphs and 100% coincides with the continual setting in Table 7. QA uses the same Qwen3-8B reader as the main experiments.
| Processed Conversations | 0% | 10% | 20% | 30% | 40% | 50% | 60% | 70% | 80% | 90% | 100% | Δ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LoCoMo F1 (GPT-5-mini) | 31.94 | 32.49 | 32.75 | 33.65 | 33.50 | 34.18 | 35.28 | 35.80 | 36.75 | 37.15 | 38.43 | +6.49 |
| LoCoMo F1 (gold labels) | 31.94 | 32.66 | 33.00 | 34.08 | 34.69 | 35.12 | 36.38 | 37.06 | 38.18 | 38.69 | 39.89 | +7.95 |
| PersonaMem-32K ACC (GPT-5-mini) | 53.99 | 54.50 | 54.84 | 55.52 | 55.86 | 56.71 | 57.05 | 56.88 | 57.72 | 58.57 | 59.59 | +5.60 |
| PersonaMem-32K ACC (gold labels) | 53.99 | 54.84 | 55.18 | 56.03 | 56.54 | 57.89 | 58.40 | 59.59 | 60.27 | 61.29 | 62.31 | +8.32 |
- Gains keep accumulating rather than saturating. With gold-label verification, performance increases at every checkpoint, reaching +7.95 F1 on LoCoMo and +8.32 ACC on PersonaMem-32K. At the query level, 650 LoCoMo queries improve versus 230 that degrade (p < 1e-40), and 65 versus 16 on PersonaMem-32K (p < 1e-7).
- The same trend holds without gold labels. With GPT-5-mini verification, the gains reach +6.49 and +5.60. The only dips (40% on LoCoMo and 70% on PersonaMem-32K) are small and come from occasional false positives of the LLM verifier, and the curves recover at the next checkpoint.
Together, Table 7 and the stream analysis show that continual evolution is tested and supported: repairs consolidated from past interactions benefit future queries, and the benefit grows as more interactions are processed. The stream analysis has been added to Appendix C.4 (Page 23), highlighted in dark red.
Response to Reviewer SiQX [Part 3]
3. The Direct-Use Ablation of the Extractor
Your Concern (W3): The extractor already identifies the evidence passages among the top 25 results, so the gain may come from this selection rather than from editing the graph.
Thanks for this valuable point. If the gain came from selection alone, then giving the reader the passages selected by the extractor, without any graph edit, should perform as well as G-Evolver. We test this directly, and further compare with a reranker trained for the same task on the same candidates, which is a stronger form of selection than the extractor itself.
Setup. Both variants start from the same top-25 candidates as G-Evolver, and the reader always receives three passages, as in the main experiments.
- Extractor only. The same trained extractor checkpoint selects evidence from the top-25 candidates, but no graph edit is performed. The selected passages are placed first in the reader's context, and the remaining slots are filled in the original retrieval order.
- Task-trained reranker. A Qwen3-8B reranker is trained with GRPO on the same 500 training queries, using the retrieval score in
Eq. (6)as the reward and the same training budget as the other training-based baselines (150 steps, 8 queries per step, 4 rollouts per query). Its top-3 passages among the same top-25 candidates are passed to the reader.
| Extractor only | Task-trained reranker | G-Evolver | |
|---|---|---|---|
| LoCoMo F1 / Judge | 34.78 / 54.46 | 36.72 / 56.89 | 37.48 / 58.02 |
| LongMemEval-S F1 / Judge | 34.02 / 45.18 | 35.87 / 47.80 | 36.44 / 48.57 |
| PersonaMem-32K ACC / MRR | 55.18 / 73.08 | 57.56 / 75.22 | 58.74 / 75.89 |
| PersonaMem-128K ACC / MRR | 46.10 / 66.55 | 48.22 / 68.31 | 49.17 / 68.87 |
| PrefEval-Explicit ACC / MRR | 74.50 / 83.45 | 77.10 / 85.53 | 78.00 / 86.08 |
| PrefEval-Implicit ACC / MRR | 55.30 / 70.82 | 57.50 / 72.08 | 58.70 / 72.81 |
Analysis.
- Selection alone does not explain the gain. With the same extractor and the same candidates, removing graph editing lowers performance by 2.0–3.6 points on every metric of all six benchmarks, so this part of the gain can only come from the edits. The extractor's output is also not meant to be a final answer context: it selects the passages that the evolver may edit, and its reward includes the evolution gain (
Eq. (8)), so it may keep passages that are useful for linking to the evidence but do not contain the answer themselves. - Even a selector trained for this task falls short. The task-trained reranker is stronger than the extractor, but G-Evolver still leads on every metric, by 0.55–1.20 points. Any selection method can only reorder the fixed top-25 candidates. G-Evolver instead changes the graph and reruns Personalized PageRank on the modified structure (
Eq. (4)), so its edits change how relevance propagates and can bring in evidence that no reordering of the original candidates would reach. - Edits also benefit later queries, which selection cannot do. A selection is made for one query and leaves nothing behind. Graph edits persist: as shown in our response to W2, edits consolidated from earlier queries further improve later ones (
Table 7), a benefit that selection by construction cannot provide.
Therefore, selecting evidence among the top-25 candidates, even with task-specific training, cannot account for the improvement of G-Evolver, and the remaining gain comes from repairing the graph. This ablation and the task-trained reranker comparison have been added to Appendix C.7 (Page 25), highlighted in dark red.
Thanks again for the time and effort you have invested, and we apologize once again for our delayed response. We would be sincerely grateful if you could find some time to go over our rebuttal!
We hope these responses address your concerns comprehensively. Feel free to let us know if you have any additional questions, and we are more than happy to provide further clarification on any aspect of our work.
Respectfully and sincerely,
The Authors
Response to Reviewer SiQX [Part 1]
Dear Reviewer SiQX:
Thank you so much for your thoughtful review and valuable feedback. We deeply appreciate the time and effort you devoted to evaluating our work.
We also sincerely apologize for the delay in our response. To address your comments as thoroughly as possible, we conducted a substantial number of additional experiments, along with a dedicated round of human annotation. Some of these experiments were completed only very recently, and we truly appreciate your patience. Below, we have provided detailed responses to your comments.
1. The Novelty of G-Evolver
Thanks for this comment, and we apologize for any confusion. We first clarify the FluxMem reference, and then discuss FluxMem and Memory-R1 separately.
(1) Clarification of the FluxMem Reference. The FluxMem that we identify as the closest work in
Appendix Eis Fang et al. (2026), "Rethinking Memory as Continuously Evolving Connectivity" (arXiv:2605.28773). The reference [1] listed in the review, "FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding" (Xie et al., 2026, arXiv:2603.02096), is a different paper that shares the same name. It is a training-free visual token compression method for streaming video understanding with multimodal LLMs: it removes redundant visual tokens across adjacent frames and merges spatially redundant regions within each frame. It involves neither a memory graph nor retrieval feedback, and therefore does not repair graph links. Below, we discuss Fang et al. (2026), the work cited in our paper.(2) Difference from FluxMem (Fang et al., 2026). First, FluxMem is a training-free method: when execution fails, an LLM is prompted to attribute the failure and choose an edit. G-Evolver instead learns where to edit (the extractor) and how to edit (the evolver) with GEPO, where each module and each operation is credited by the retrieval gain it brings to the query and its neighboring queries. Second, the two methods address different scenarios. FluxMem targets agentic task execution, such as web navigation on Mind2Web and general assistant tasks on GAIA, organizing memory into semantic, episodic, and procedural layers, and its feedback is the success signal of task execution or self-verification at each step. G-Evolver targets graph memory built over long-term interaction histories, such as HippoRAG2-style entity–passage graphs, and its feedback is whether a query retrieves the passages it requires. Third, the two methods edit different objects. FluxMem's link expansion and pruning act on the subgraph activated for the current step, connecting memory nodes to or disconnecting them from the current step anchor to refine the context of that step, and its long-term stage distills successful trajectories into procedural skills. G-Evolver edits the structure among stored memories themselves, namely the triples extracted from each passage and the edges between passages, and only edits that improve the current query without degrading any neighboring query are consolidated into the persistent graph to serve later queries. Regarding the comparison, FluxMem was released on arXiv on May 27, 2026, shortly before our submission, and its code had not been released at that time, so we could not faithfully compare against it under our setting.
(3) Difference from Memory-R1. The operations of G-Evolver and Memory-R1 act on fundamentally different objects. Memory-R1 manages a flat bank of textual memory entries: when a new dialogue turn arrives, its Memory Manager decides whether to ADD, UPDATE, or DELETE a stored entry or leave it unchanged (NOOP), and it is rewarded by whether the downstream Answer Agent answers correctly. It maintains no graph and no links between entries. G-Evolver never modifies the stored memory text. It edits the graph built over the memory: inserting a triple that a passage states but its extraction misses, linking two related passages with a semantic edge, and rewriting a triple that misrepresents its source passage, which itself stays unchanged. These edits are triggered at query time by the retrieval defects a query exposes, rather than at write time by incoming information, and are rewarded by the retrieval gain on the query and its neighboring queries rather than by answer correctness. In short, Memory-R1 decides what is stored, whereas G-Evolver decides how the stored memories are connected for retrieval.
We have revised
Section 5and added a detailed comparison with FluxMem and Memory-R1 toAppendix E.3(Page 30), highlighted in dark red.