- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces GenRevisit, an image-generation agent that chooses a previously generated image and an instruction for editing it. Training combines selective teacher-guided SFT with NACA, which allocates positive trajectory advantages based on normalized progress at each step. Experiments cover three compositional benchmarks, transfer across image generators, training ablations, and comparisons with controlled access to source images. GenRevisit achieves a GM score of 84.3 on GenEval2.
Critical strengths
- The method addresses a concrete failure of iterative editing: later edits can destroy previously satisfied constraints. Historical source selection provides a practical recovery mechanism.
- Strong reported benchmark results are complemented by matched-prefix comparisons, providing evidence beyond selected qualitative examples.
Critical weaknesses
- The final trained policy is not directly compared under Joint, Best-only, and Latest-only access with otherwise identical settings. The archived student study always selected the current best during historical edits, leaving the central claim of beneficial non-best source selection insufficiently established.
- NACA is compared mainly against standard GRPO, without simpler action-credit baselines or multi-seed results. Its specific normalization benefit and robustness are therefore unclear.
Questions for authors
- With the final checkpoint fixed, how does performance change under Joint, Best-only, and Latest-only source access? How often do beneficial edits use a source that is neither latest nor best?
- Are NACA’s gains consistent across training seeds, and how does it compare with simply removing positive credit from regressive actions?
- Does “two-seed selection” in Figure F.7 apply only to qualitative examples or also to the reported GenEval++ scores?
3 comments
Q2: NACA Robustness and Regressive-Action Masking
We agree that removing positive credit from regressive actions is a meaningful alternative to NACA. Our motivation is to distinguish meaningful progress during iterative refinement: binary masking identifies whether an action improves its selected source, while NACA further differentiates the relative progress made by improving actions. The qualitative cases below illustrate these two aspects.
Case A: Binary Masking vs. NACA (a bear and four glass horses)
| Editing action | Observed effect | Masking | NACA | |
|---|---|---|---|---|
| Edit 1 | Counting error remains | 0.0008 | 1.000 | 0.002 |
| Edit 2 | Counting error remains | 0.0038 | 1.000 | 0.007 |
| Edit 3 | Fourth horse added; count resolved | 1.2281 | 1.000 | 2.396 |
Although all three edits yield positive utility gains, only the final edit resolves the remaining counting constraint. Masking assigns equal positive credit, whereas NACA places substantially greater weight on the effective repair.
Case B: Absolute Improvement vs. NACA (a metal raccoon to the right of two suitcases)
| Editing action | Observed effect | Absolute | NACA | |
|---|---|---|---|---|
| Edit 1 | Material and count repaired | 1.1689 | 0.638 | 0.724 |
| Edit 2 | Identity restored; prior gains preserved | 1.0807 | 0.590 | 1.394 |
Despite similar absolute utility gains, the second edit closes nearly all of its remaining utility gap (99.97%, compared with 51.95% for the first edit), restoring the raccoon's identity while preserving the previously established material and count requirements. NACA assigns greater credit based on normalized progress, whereas absolute-gain allocation assigns similar weights to both actions.
The reported coefficients are obtained by offline reweighting of fixed trajectories, using proxy action-token lengths and a trajectory advantage of . They illustrate the allocation mechanism rather than results from separately trained policies.
To assess robustness and compare against simpler alternatives, we evaluate standard GRPO, regressive-action filtering, absolute-improvement allocation, and NACA. NACA achieves 84.30 and 84.14 GM across two independent training runs, demonstrating consistent results across different training seeds. Regressive-action filtering achieves 83.1 GM, and absolute-improvement allocation achieves 82.9 GM. NACA improves GenEval2 GM by 4.0 points over standard GRPO, 1.2 points over regressive-action filtering, and 1.4 points over absolute-improvement allocation.
| Credit assignment | GenEval2 GM | NACA gain (GM) |
|---|---|---|
| Standard GRPO (two-seed average) | 80.3 | +4.0 |
| Regressive-action filtering | 83.1 | +1.2 |
| Absolute-improvement allocation | 82.9 | +1.4 |
| NACA (two-seed average) | 84.3 | — |
Q3: Clarification on Two-Seed Selection in Figure F.7
Thank you for pointing out this ambiguity, and we apologize for the unclear wording in Figure F.7. The two-seed selection applies exclusively to the qualitative examples in Figure F.7. The GenEval++ overall score of 89.3 reported in Table 2(b) was obtained by averaging results from two seeds across all 280 prompts, following the same evaluation protocol for both seeds. We are clarifying this distinction in the revised figure caption.
We are revising the manuscript and preparing the supplementary material for upload to incorporate these results and clarifications.
We sincerely appreciate your time and valuable suggestions. Your thoughtful feedback has helped us further strengthen the experimental validation and improve the clarity of our work. Thank you again for your careful review and constructive comments.
Additional Baselines and Component Ablations for NACA
Thank you again for raising the question of whether NACA's improvements arise from its specific credit-assignment design. In our previous response, we compared NACA against standard GRPO, regressive-action filtering, and absolute-improvement allocation. To further strengthen this analysis, we have conducted additional controlled comparisons, including credit-conserving filtering, an EditThinker-inspired Differential GRPO baseline, and an ablation of credit capping.
The complete results are summarized below:
| Training Method / Configuration | GenEval2 GM |
|---|---|
| Standard GRPO | 80.3 |
| Regressive-action Filtering | 83.1 |
| Absolute-improvement Allocation | 82.9 |
| Credit-Conserving Filtering | 83.3 |
| EditThinker-inspired Differential GRPO | 82.6 |
| NACA without Capping | 84.1 |
| NACA (Ours) | 84.3 |
These comparisons examine three complementary aspects of NACA's design: remaining-gap normalization, token-weighted credit redistribution, and credit capping.
(1) Remaining-gap progress normalization. To examine the role of remaining-gap normalization, we compare NACA against absolute-improvement allocation, which distributes credit according to absolute utility gains rather than remaining-gap-normalized local progress, while retaining the same token-weighted credit redistribution and credit capping. NACA achieves 84.3 GM, compared with 82.9 GM for absolute-improvement allocation (+1.4). This supports the benefit of accounting for the remaining improvement gap when measuring the relative progress of individual editing actions.
(2) Credit allocation under a conserved budget. Regressive-action filtering removes positive credit from non-improving actions, thereby reducing the total token-weighted positive credit mass. We introduce credit-conserving filtering to control for this change by restoring the original credit mass while assigning equal per-token advantages to retained actions. NACA achieves 84.3 GM, compared with 83.3 GM for credit-conserving filtering (+1.0). This demonstrates that conserving the total credit budget alone is insufficient; credit must also be differentiated according to the progress made by individual actions.
(3) Credit capping. We further conduct an ablation by removing credit capping while keeping the other NACA components unchanged. The resulting model achieves 84.1 GM, compared with 84.3 GM for the full method (+0.2). This small difference is consistent with the rare occurrence of extreme credit allocations observed in our training trajectories, suggesting that credit capping primarily serves as a safeguard against excessive credit concentration, rather than being the main source of NACA's performance gains.
Comparison with differential-reward training. We additionally implement and train an EditThinker-inspired Differential GRPO baseline adapted to GenRevisit. The baseline combines differential rewards with step-wise group-relative optimization over candidate joint actions. This provides a direct empirical comparison between local differential-reward optimization through step-wise GRPO and NACA's trajectory-level optimization with source-relative action credit assignment. The results show that the adapted Differential GRPO provides a competitive approach to multi-round policy optimization. Nevertheless, NACA achieves a further 1.70 GM improvement, highlighting the benefit of its trajectory-level optimization and source-relative action credit assignment.
Taken together, these experiments support the complementary roles of NACA's three design components. NACA combines remaining-gap normalization, progress-aware credit allocation under a conserved token-weighted budget, and credit capping while retaining the trajectory-level terminal objective.Together, these mechanisms provide an effective credit-assignment approach for multi-round refinement.
We sincerely thank you again for your thoughtful review and constructive suggestions. We hope these additional experiments and analyses further clarify the motivation and empirical effectiveness of NACA's design, and provide stronger empirical support for its role in multi-round refinement. We greatly appreciate your time and consideration.
Response to Reviewer XZcR
Thank you for the constructive assessment and for identifying the need for more direct validation of the final policy and NACA. Your comments have helped us organize additional controlled source-access evaluations, clarify the credit-assignment analysis, and make the evaluation protocol more explicit. We respond to each question below.
Q1: Joint Source Selection and Non-Best Continuations
To directly address this concern, we evaluate the same final RL checkpoint under three source-access settings: Latest-only, Best-only, and Joint. All settings start from the same initial images and follow the same evaluation protocol, with only the set of eligible editing sources differing.
Our objective is not to maximize non-best selections, but to avoid restricting continuation to a fixed strategy. While best-only may work well in many cases, the highest-scoring image is not necessarily the most promising starting point for every subsequent edit. Joint selection allows the policy to choose the current best, the latest image, or another historical candidate, depending on the remaining errors and the editing instruction suited to each source. Through this process, the policy implicitly learns to assess the continuation potential of different candidates and determine where and how to continue.
To further characterize this behavior, we examine how frequently the Joint policy selects sources that are neither the latest nor the current GM-best. Of the 800 trajectories, 445 contain at least one editing action, with 1,267 editing actions in total. Source-selection frequencies use these editing actions as the denominator; initial generation and regeneration calls are excluded. Such selections account for 6.24% (79/1,267) of all editing actions, and 63.29% (50/79) of these edits produce a new candidate surpassing the historical GM-best. This frequency is not an optimization target; the value of Joint selection lies in learning when different continuation states are useful, rather than enforcing a fixed preference for any particular source.