- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper introduces DAYDREAMBENCH and DAYDREAMER. The benchmark connects 201 author personas with synthetic episodic MemoryBanks containing 46,959 first-person memories, including flows of 3–6 scenes reverse-constructed from source works. The memories are presented as plausible synthetic writing resources. The test set contains 343 tasks with personas held out from training and validation. DAYDREAMER separates a Writer from a Qwen3.5-2B Walker that navigates the MemoryBank through explicit actions. The Walker receives SFT on 470 trajectories followed by GRPO using writing-outcome, reference-based navigation, process, and protocol rewards; the direct incremental surface-recall reward is disabled in the reported run (Appendix B.3). With the Qwen writer, training increases surface recall from 0.395 to 0.508 and overall judge score from 76.89 to 77.75; the GPT-6 Luna writer's overall score increases from 82.08 to 82.89. Appendix F provides paired tests for navigation metrics, with the most consistent improvements in memory discovery and smaller, comparator-dependent improvements in final selection.
Critical strengths
- A useful formulation of sequential memory use. The separation of navigation from writing enables executable trajectory supervision and intermediate measurements of discovery, retention, and selection. This makes it possible to examine where a memory-augmented system succeeds or fails beyond the final generated text. The persona-disjoint evaluation also provides evidence of generalization to held-out personas within the constructed benchmark.
- Navigation improvements are evaluated with appropriate qualifications. Appendix F reports significance tests and bootstrap intervals. Keep Recall is not significantly higher than the base Walker (Holm-adjusted p = 0.7201), but improves over retrieval and Graph-PPR baselines. Selected F1 improves over the base Walker and Graph-PPR, with positive bootstrap intervals; against RAG/RAG+Reranking, the favorable sign test accompanies an interval that slightly crosses zero. Thus, the evidence supports both discovery and some final-selection improvements, with stronger consistency for discovery.
Critical weaknesses
- Independent validation of the reference construction and writing assessment is limited. The synthetic reference flows define several training rewards and navigation metrics. This supports measuring recovery of the constructed references, but does not establish that those references adequately represent the range of useful associations. The evaluation judge prompt in Appendix C, Table 11 also supplies reference memories and uses them when assessing persona grounding and creative transformation, so the writing scores are not fully independent of this construction. Useful non-reference memories could consequently be undervalued. Alignment of training and evaluation criteria does not make improvements on held-out personas automatic, but stronger independent validation is needed to interpret them as improvements in associative usefulness or creative writing quality.
- The incremental writing benefit of learned navigation remains uncertain. Overall writing-score gains over RAG+Reranking are 0.73 points for Qwen3.6-27B (77.75 vs. 77.02) and 0.50 points for GPT-6 Luna (82.89 vs. 82.39), without paired uncertainty estimates for these differences or human evaluation of the generated writing. Overlap between judge and generation model families warrants a sensitivity analysis, although it does not by itself demonstrate self-preference. The larger persona-grounding gain over Persona-only jointly reflects access to memories and the navigation strategy; it cannot isolate the contribution of learned navigation. The relevant incremental comparisons are against memory-augmented retrieval and the base Walker.
Questions for authors
- Can you provide paired confidence intervals and significance tests for writing-quality differences against RAG+Reranking and the base Walker, separately for each Writer?
- Can independent human raters evaluate generated writing without being required to reward agreement with the constructed reference flow? A useful accompanying check would assess the plausibility and usefulness of both reference and non-reference memory selections.
- How stable are the writing rankings when reference memories are omitted from the judging prompt, and when judges sharing a model family with the Writer or dataset generator are excluded?
- How sensitive are navigation results to alternative plausible reference flows or a different construction model? The relevant target is useful synthetic writing resources, consistent with the paper's stated scope.
- Since the retrieval arms share a base-Walker selector, can you add a direct RAG-to-Writer baseline to isolate the contribution of that shared selection stage?
3 comments
Response to Reviewer iJFD (2)
R3(Q4). Robustness to changes in the associative memory structure
Our original benchmark already adopts a persona-disjoint split, ensuring that training and test personas do not overlap. The evaluation therefore involves previously unseen personas and their corresponding MemoryBanks, providing initial evidence that the learned policy transfers across persona-specific memory environments and is robust to changes in the associative memory structure.
Secondly, to test whether the learned Walker depends on the particular associative structure present during training, we conducted an additional memory-graph perturbation experiment, without any additional training. Specifically, we perturb the memory traversal graph through semantically constrained edge rewiring:
- Rewired concepts must be type-compatible with the original concepts, previously unconnected to the corresponding episode, and have an embedding cosine similarity of at least 0.70 to the original concepts.
- We preserve each episode’s degree and constrain changes in concept-node degrees to avoid unrealistic graph corruption. Episode texts, memory IDs, embeddings, personas, writing tasks, Memory Requests, gold reference flows, and schema nodes remain unchanged.
We then evaluate 10% and 30% edge rewiring and all graph-aware methods operate on the same perturbed graph. We evaluate 20 held-out personas from our test split (randomly select 10 from PoetryDB and 10 from Gutenberg), covering 164 writing tasks, and compare four methods: trained Daydreamer, Base Walker, RAG + Reranking, and Graph-PPR.
Results. The following table reports persona-level macro-averaged Surface Recall. Perturbed results are averaged over three random seeds, with standard deviations shown.
| Method | Original Graph | 10% Rewiring | 30% Rewiring |
|---|---|---|---|
| Daydreamer | 0.481 | 0.457 ± 0.024 | 0.469 ± 0.014 |
| Base Walker | 0.350 | 0.344 ± 0.007 | 0.344 ± 0.004 |
| RAG + Reranking | 0.395 | 0.394 ± 0.000 | 0.394 ± 0.001 |
| Graph-PPR | 0.365 | 0.360 ± 0.003 | 0.344 ± 0.005 |
Daydreamer consistently outperforms all baselines even when the underlying associative graph is modified. Notably, under 30% edge rewiring, it achieves a Surface Recall of 0.469, compared with 0.344 for Base Walker and 0.394 for RAG + Reranking. Since the Walker is not retrained, these results suggest that the learned policy remains effective when navigating modified memory structures.
Together with our persona-disjoint evaluation, these findings support our central claim that Daydreamer learns a transferable, observation-conditioned policy for sequential associative memory navigation, rather than a strategy tied to a particular memory graph.
R4(Q5). Direct RAG baseline and the contribution of the shared selector
We would like to explain that our original motivation for applying the same selector to the retrieval baselines was to control for the final selection stage: without this control, differences between RAG and Daydreamer could conflate navigation/retrieval quality with the effect of an additional selector. Nevertheless, following your suggestion, we added a Direct RAG baseline in which the dense-retrieval Top-K memories are passed directly to the Writer without any Walker-based selection. We set (k=7) to match the average number of memories retained by the selector across test tasks, thereby avoiding an advantage from simply providing the Writer with more retrieved memories.
The results are:
| Method | Surface Recall | Keep Recall | Selected F1 | Flow Align. | Overall |
|---|---|---|---|---|---|
| Direct RAG | 39.6 | 28.4 | 19.3 | — | 79.68 |
| RAG + Reranking | 39.7 | 25.9 | 19.8 | — | 82.39 |
| Daydreamer | 52.2 | 32.0 | 22.6 | 19.4 | 82.89 |
First, the comparison shows that the shared selection stage itself improves downstream writing quality. This supports our original motivation for controlling the selector when comparing retrieval methods. Second, even after controlling for this shared selection stage, Daydreamer achieves higher navigation coverage and the final writing score.
Revised Manuscript and Further Discussion
Thank you for your suggestions. We have now uploaded the revised manuscript, incorporating additional experiments, analyses, and clarifications to address the reviewers' concerns. We sincerely invite you to review the updated manuscript and welcome any further questions or discussion.
Response to Reviewer iJFD (1)
R1(W1, Q2, Q3). Reference-independent validation of writing quality and memory usefulness
We would first like to clarify an important distinction regarding the term “reference memories” in our evaluation prompt.
The memories provided to the writing Judge are not the gold reference-flow memories used to construct the training rewards and navigation metrics. Rather, reference memories are the memories actually retrieved and selected by each method and supplied to the Writer as writing references. The Judge does not observe the gold reference flow, gold memory set, or whether a selected memory belongs to that set. It only observes the memories available to the Writer and evaluates whether the generated text meaningfully grounds in and creatively transforms those memories.
Therefore, a memory is not penalized simply because it falls outside the constructed gold reference flow, since the Judge has no access to that membership information. A non-gold memory discovered by Daydreamer can receive full credit if it provides useful material for the resulting writing.
Following your suggestion, we conducted an additional human evaluation during the rebuttal period. We recruited 40 participants with an interest in literature and randomly sampled 50 writing tasks from the poetry portion of the test set to form the evaluation pool. Each participant was randomly assigned ten tasks. For each task, the participant compared anonymized outputs from four systems:
(1) Persona-only; (2) RAG + Reranking; (3) Base Walker; and (4) Daydreamer
Participants were not shown the method identity, retrieved memories, gold memories, or reference flows. They were asked to select the overall best poem based on four aspects of literary quality: language and imagery, poetic technique, originality, and emotional/aesthetic impact. They could also select “Tie / difficult to distinguish” when no output was clearly preferable.
The aggregate preferences are:
Daydreamer receives the highest human preference rate (24.9%) among the four systems. Importantly, this evaluation is completely independent of the constructed reference flows: annotators judge only the final writing and are never instructed to reward agreement with any reference memory or reference trajectory.
R2.(W2, Q1, Q3) Statistical reliability and judge-family sensitivity
We performed an additional reference-free pairwise evaluation over all 343 test writing tasks, comparing:
For each task, the two generated texts were anonymized and randomly assigned to positions A/B. Importantly, the evaluator was shown only the two generated texts: it did not observe the method identity, persona, retrieved memories, gold reference memories, reference flow, or navigation trajectory. The evaluator judged only the literary quality of the outputs and returned A, B, or Tie.
We evaluated the outputs using four independent model judges: Qwen, GPT-6 Luna, DeepSeek, and GLM. The resulting macro-persona preference rates are:
The preference for Daydreamer therefore persists when GPT-6 Luna is excluded, addressing the concern about overlap between the Writer and Judge model families. Across the test tasks, the paired comparisons remain statistically significant after Holm correction, with one-sided adjusted p-values of: (1) Daydreamer vs. Base Walker: p = 0.0439; (2) Daydreamer vs. RAG + Reranking: p = 0.0424