- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies why the benefits of reasoning vary across BAGEL image-editing tasks. PRISM predicts task complexity, selects one to three instance-specific reasoning lenses, executes them sequentially, and consolidates their outputs into three actions before a single image-generation step. The understanding and generation experts are trained with GRPO and early-window Flow-GRPO, respectively. The authors also construct the 50,000-example REVISE-50K dataset and report improvements over the listed baselines on KRIS, RISE, and PICABench-Superficial, alongside better direct-editing performance (Table 2). The contribution primarily combines complexity routing, structured planning, generation training, and dataset design, rather than introducing a new foundational optimization algorithm.
Critical strengths
- The improvements span multiple settings rather than only difficult edits. In Table 2, PRISM reaches 73.2, 15.27, and 64.32 on KRIS, RISE, and PICA-Superficial, respectively. These correspond to gains of approximately 13.0, 3.4, and 17.8 score units over BAGEL-Think, rather than relative percentages. GEdit-R and ImgEdit also improve from 5.06 and 3.0 to 7.00 and 4.00. Although PRISM does not lead every direct-editing baseline, these results provide encouraging evidence of the combined method's practical potential.
- The authors make a substantive effort to isolate sources of improvement and validate supervision. Tables 4 and 9 distinguish the effects of generation RL, the reasoning framework, and training data. In Table 5, always-Heavy structured reasoning achieves 73.4 on KRIS, while the adaptive version recovers GEdit from 6.37 to 7.00, illustrating a useful quality trade-off. The complexity study has three annotators rate the same 1,000 examples, reports teacher–human-consensus quadratic weighted kappa (QWK) of 0.608, and candidly notes inter-annotator agreement of only 0.458 (Section 5.3). The window-variance measurements also provide empirical motivation for the early window; these analyses should not be treated as absent.
Critical weaknesses
- The mechanistic interpretation exceeds what the controls establish. Although Table 5 controls GRPO, data, and budget, it lacks an adaptive-but-unstructured variant and corresponding fixed-Light/Moderate results. Table 1 compares fixed word budgets and evaluates textual reasoning rather than final edits, so it cannot rule out simpler budget policies. There is also a concrete inconsistency in the CFG diagnostic: without CFG, Figure 3 calls for comparing KRIS scores of 48.5 and 42.9, whereas Section 3.2 describes the effect as 55.0 to 42.87, crossing CFG settings. The negative effect remains, but attributing the full 12.1-point drop to reasoning alone is not justified. The safer conclusion is that the combined design works in this BAGEL configuration, not that adaptivity and structure are universally “jointly necessary.”
- Validation of the evaluation underlying the quality claims remains incomplete. This work reasonably adds preservation as an evaluation dimension, but also switches to a GPT-5.2 judge and replaces the original GEdit protocol with a three-aspect geometric mean. It states that the authors conducted blinded preference comparisons on 200 GEdit and 200 KRIS examples, as well as a 300-example comparison of the old and new protocols, yet preference rates, agreement with human judgments, and uncertainty estimates are not reported. The human study in Section 5.3 validates complexity labels and cannot substitute for output-quality validation. Tables 2–5 also lack confidence intervals for the main scores or repeated-training results, leaving small differences and ranking stability under the new metric uncertain. This is an evidence gap, not proof that the judge is necessarily biased.
Questions for authors
- Could you add adaptive free-form CoT and fixed-Light/Moderate controls to Table 5, reporting final editing quality and actual token costs by complexity level? Could you also recompute the effect sizes in Figure 3 and Section 3.2 while holding CFG fixed?
- What exactly does the “20-fold” cost reduction measure? Please provide a comparison with EditThinker under matched hardware, resolution, and quality settings, including complexity prediction, lens generation and execution, and action generation in the end-to-end cost.
7 comments
Response 1, Part 2
(c) Effect sizes at fixed CFG. Table R3 reports the effect of reasoning at fixed CFG, computed from the four cells of Figure 3.
Table R3. KRIS for BAGEL, from Figure 3, with the effect of reasoning at fixed CFG.
| Without CFG | With CFG | |
|---|---|---|
| Without reasoning | 48.5 | 55.0 |
| With reasoning | 42.9 | 60.0 |
| Effect of reasoning | −5.6 | +5.0 |
At fixed CFG, reasoning lowers KRIS by 5.6 points without CFG and raises it by 5.0 with CFG. These within-setting effects support Observation 2 directly: the sign of the effect of reasoning depends on generation adherence. Equivalently, CFG adds 6.5 points without reasoning but 17.1 with it. On GEdit, reasoning lowers the score at either CFG setting. The revision reports these within-setting effects in Section 3.2 and in the caption of Figure 3.
(d) Scope of the claim. We agree, and we state the scope of each claim precisely. Our evidence has two levels of generality. The diagnosis, that reasoning helps reasoning-intensive edits and hurts direct ones, holds on three editors (Table R4; Appendix D.10).
Table R4. Effect of reasoning on three editors. BAGEL uses its own thinking mode; for OmniGen2 and Qwen-Image-Edit, reasoning is generated by Qwen2.5-VL and prepended to the instruction.
| Backbone | GEdit: no reasoning → reasoning | KRIS: no reasoning → reasoning |
|---|---|---|
| BAGEL | 5.95 → 5.71 (−0.24) | 56.21 → 60.18 (+3.97) |
| OmniGen2 | 5.58 → 5.12 (−0.46) | 50.52 → 57.38 (+6.86) |
| Qwen-Image-Edit | 7.23 → 7.00 (−0.23) | 64.43 → 68.89 (+4.46) |
The remedy, and the finding that both axes are needed, are established for BAGEL trained with our recipe (Table R1). The revision states the second finding for this configuration and replaces "jointly necessary" with "both needed in our experiments".
W2. Validation of the evaluation
We add a human evaluation of output quality and of the GEdit-R protocol.
Output quality, judged by humans. Annotators compared edited images side by side, without knowing which model produced each, on 200 GEdit and 200 KRIS samples.
Table R5. Blinded pairwise human preference (n = 400 per comparison; 95% confidence interval in brackets).
| Comparison | PRISM preferred | Baseline preferred | Tie |
|---|---|---|---|
| PRISM vs BAGEL-Think | 84% [80.4, 87.6] | 8% | 8% |
| PRISM vs Qwen-Image-Edit | 68% [63.4, 72.6] | 27% | 5% |
Both preferences are significant (p < 0.001, two-sided sign test excluding ties).
Agreement of GEdit-R with humans. On 300 GEdit samples, GEdit-R agrees more closely with the human ranking than the original protocol (Spearman ρ = 0.81 vs 0.64).
The modified protocol affects one benchmark (GEdit). KRIS, RISE, PICA and ImgEdit are scored with their released protocols and judges. PRISM's largest gains over BAGEL-Think, +13.0 on KRIS, +3.4 on RISE and +17.8 on PICA, are therefore measured under unmodified protocols, as is its ImgEdit gain (3.0 to 4.00). The Table 1 diagnostic also holds under Gemini as a second judge (length budgets 6.4 to 6.7, structured variant 7.9).
Uncertainty. We repeated the GPT-based evaluation of every benchmark four times. The judge variability is 0.15 on GEdit, 0.1 on ImgEdit, 1.0 on KRIS, 0.4 on RISE and 1.5 on PICA. Our conclusions rest on differences well above these levels: PRISM's gains over BAGEL-Think are 1.29 on GEdit, 1.0 on ImgEdit, 13.0 on KRIS, 3.4 on RISE and 17.8 on PICA, between 8 and 13 times the judge variability of each benchmark. Within the controls, structure adds 10.8 points on KRIS and adaptivity 0.63 on GEdit (Table R1). Differences within the judge variability, such as 7.00 vs 7.08 on GEdit (Table 6), we report as ties and draw no conclusion from. Appendix D.9 reports the judge variability (Table 13).
Revision: Section 5.3 reports the human study (Table 5) and the GEdit-R validation; Appendix D.8 gives the study protocols, and Appendix D.9 the judge variability (Table 13).
Response 1, Part 3
Q2. What the 20× measured, and a matched comparison with EditThinker
Measurement. We timed every method end to end on one A100 GPU at batch size 1, from the input image and instruction to the final edited image, with BAGEL as the editor throughout. For PRISM, the timing includes all four stages: complexity prediction, lens generation, lens execution and action generation. For EditThinker, it includes every verifier call and regeneration.
Table R6. Latency per edit.
| Method | Setting | Images per edit | Latency (s) | Relative to PRISM |
|---|---|---|---|---|
| BAGEL | 512 px, 25 steps | 1 | 11.5 | 0.61× |
| BAGEL-Think | 512 px, 25 steps | 1 | 16.6 | 0.88× |
| PRISM | 512 px, 25 steps | 1 | 18.8 | 1.00× |
| BAGEL + EditThinker | 512 px, 25 steps | 3.1 | 43.4 | 2.3× |
| BAGEL-Think + EditThinker | 512 px, 25 steps | 3.5 | 63.8 | 3.4× |
| BAGEL-Think + EditThinker | 1024 px, 50 steps | ~4 | 183 | 9.7× |
| BAGEL-Think + EditThinker, all 8 rounds | 1024 px, 50 steps | 8 | 355 | 18.9× |
At matched settings, EditThinker takes 2.3 to 3.4 times as long as PRISM. All of PRISM's reasoning stages together add 7.3 s to an 11.5 s edit. EditThinker instead regenerates the image in every round, three to four times per edit on average. The 20× figure corresponds to EditThinker's worst case, all eight rounds at its default setting (1024 px, 50 steps), relative to PRISM at our setting (last row, 18.9×). The revision reports the full range, with the ratio at matched settings as the headline.
Quality at that cost.
Table R7. EditThinker on top of BAGEL and of PRISM.
| Model | GEdit | KRIS |
|---|---|---|
| BAGEL | 5.95 | 56.2 |
| BAGEL + EditThinker | 6.22 | 62.8 |
| PRISM | 7.00 | 73.2 |
| PRISM + EditThinker | 6.71 | 75.6 |
PRISM alone outperforms BAGEL with EditThinker on both benchmarks (+0.78 on GEdit, +10.4 on KRIS) at less than half its latency. On top of PRISM, the verifier adds 2.4 points on KRIS but lowers GEdit by 0.29, which reproduces, one level up, the overthinking pattern of Section 3.2.
Revision: Section 5.2 adds the comparison with EditThinker (Table 3), and Appendix D.12 gives the full latency measurements and the protocol (Table 18).
We thank the reviewer again for the precise requests. They led to the full grid over adaptivity and structure, scored on final edits, to effect sizes at fixed CFG, to the human evaluation of output quality, and to a matched cost comparison that includes every stage of PRISM. We have also scoped the necessity claim as the reviewer suggested. We hope that these results address the reviewer's concerns, and we would be glad to discuss any remaining questions during the discussion period.
Response 1, Part 1
We apologize for posting our response late in the discussion period. We used the time to run all the experiments and comparisons that the reviewers requested, so that each concern is answered with new evidence. We would be grateful for the reviewer's response and feedback at their earliest convenience, which would let us make the best use of the remaining discussion period and address any further concerns in a timely manner.
Table, figure and appendix numbers in this response refer to the revised paper; where the review cites a number from the submission, we give both.
We thank the reviewer for the detailed and balanced review. We are glad that the reviewer found the improvements broad, spanning reasoning-intensive and direct editing (S1), and our effort to isolate the sources of improvement and to validate the supervision substantive (S2). We have run each of the controls the reviewer requested. We answer W1 together with Q1, then W2 and Q2; all changes are included in the revised paper.
W1 / Q1. Do the controls support adaptivity and structure as jointly necessary?
(a) Adaptive free-form and fixed-level controls (new). We add the three requested controls, so that Table 7 (Table 5 in the submission) becomes a full grid over adaptivity and structure, scored on the final edits. The adaptive free-form variant selects a Light, Moderate or Heavy budget per sample, as PRISM does, but reasons in free form. All rows share the GRPO recipe.
Table R1. Table 7 of the revised paper.
Adaptivity without structure improves neither benchmark. The adaptive free-form variant reaches 6.50 on GEdit and 62.4 on KRIS, within the range of the fixed budgets. Free-form reasoning lowers GEdit below no reasoning at every budget (6.25 to 6.50, against 6.94), whereas structured reasoning at the Light level does not (7.00).
Structure without adaptivity is strong on one benchmark at a time. Fixed Light keeps GEdit at 7.00 but reaches only 61.4 on KRIS; fixed Heavy reaches 73.4 on KRIS but lowers GEdit to 6.37. Only PRISM matches the best fixed level on both. With an adaptive budget, adding structure raises KRIS by 10.8 points; with structure, adding adaptivity raises GEdit by 0.63.
(b) Simpler budget policies, on final edits. Table 1 indeed scores the reasoning text. Table R1 closes this gap: it scores the edited images, and its free-form rows are the simpler budget policies, three fixed budgets and a per-sample adaptive budget. None of them exceeds 62.8 on KRIS or reaches the no-reasoning score on GEdit.
Token cost by complexity level. PRISM's reasoning grows with the predicted complexity: one lens for Light and up to three for Heavy, that is, four to six sequential text calls. Table R2 (Table 15 in Appendix D.11) reports the generated tokens per edit.
Table R2. Generated reasoning tokens per edit, by predicted complexity.
Both adaptive variants scale their reasoning with complexity, by more than three times from Light to Heavy for PRISM (22 to 77 tokens), and PRISM spends no more tokens than free-form reasoning (53 against 57 on average). The two adaptive rows of Table R1 therefore differ in structure, not in budget, and structure adds 10.8 points on KRIS and 0.5 on GEdit. The budget also follows the benchmark: reasoning-intensive benchmarks contain the largest share of Heavy edits (35% on KRIS and 56% on RISE, Figure 12), so PRISM spends its reasoning where it pays off. Adaptivity matters for quality as well as cost: on direct edits, the Heavy reasoning that PRISM avoids lowers GEdit from 7.00 to 6.37 (Table R1).