DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing

Haoxiang Cao; Jiajiong Cao; Xuanpu Zhang; Changqian Yu; Chaoqun Wang

Figure 1. Two visually poor editing outcomes can require opposite cross-module update emphases. Case A : the planner captures the requested edit reasonably well, but the renderer fails to realize it, so this sample should place more corrective update weight on the renderer. Case B : the sampled plan is a less useful intermediate for the instruction, and the renderer faithfully executes it, so this sample should place more corrective update weight on the planner. DARS is designed to distinguish render-dominant from plan-dominant update needs through routing signals; when planner-side emphasis is needed, its structured slots support finer within-planner diagnosis. Teaser showing two low-scoring failure cases in a two-stage image editing pipeline that require opposite cross-module credit-assignment decisions: one should emphasize renderer correction, while the other should emphasize planner correction.

Figure 2. Free-form vs. structured planner output. With a free-form planner trace, post-render feedback remains attached to a single opaque text sequence, making within-planner credit assignment difficult. Our four-field structured answer ( Modify , Preserve , Overall , Tips ) exposes semantically distinct slots, so the same rendered rollouts can be diagnosed field by field and converted into slot-wise planner credit signals. A double-column comparison of free-form planner output and a structured four-field planner answer, showing that structured outputs enable field-wise diagnosis and within-planner credit assignment from the same rendered outcomes.

Figure 3. Framework of DARS . The structured planner produces a four-field answer; multiple plans and renderings per plan are sampled. Mean rewards across rollouts yield hardness estimates for adaptive curriculum scheduling, while reward variability is decomposed into across-plan and within-plan components to produce module-routing signals for module-specific weighting. Prefix gating further provides slot-wise planner credit signals for finer within-planner diagnosis. Framework diagram of DARS showing the structured planner, multi-plan multi-render rollouts, rollout variance decomposition, adaptive curriculum, soft module routing, and slot-wise planner optimization.

Method	KRIS-Bench	RISE-Bench	ImgEdit-Bench	GEdit-Bench-EN	PICA-Bench
Other baselines
ThinkGen ( Jiao et al., 2025 )	59.57	10.56	3.97	7.16	60.82/65.09
UniREdit ( Han et al., 2025 )	61.02	13.33	3.70	6.47	60.40/66.55
PromptRL ( Wang et al., 2026b )	61.24	10.00	3.87	6.74	51.02/60.38
Step1X-Edit-v1p2 ( Yin et al., 2025 )	62.58	11.67	4.00	7.47	56.15/60.55
UniReason 1.0 ( Wang et al., 2026a )	63.26	15.00	4.06	6.52	57.30/61.62

Table 1. Main comparison across five benchmarks. All entries are official overall scores (higher is better; compare within columns). PICA-Bench reports “simple / detailed” prompt scores. We highlight Qwen-Image-Edit-2511-based methods separately and include a controlled Joint RL + Adaptive Curriculum baseline matching DARS in backbone, data, reward model, and rollout budget.

Figure 4. Qualitative comparison on reasoning-intensive editing tasks requiring temporal, spatial, logical, physical, and world-knowledge reasoning, often in combination. Compared with baseline methods, DARS achieves the strongest overall performance, producing more faithful edits with better preservation and stronger scene-level consistency. Qualitative comparison figure for DARS, comparing source images, user instructions, baseline outputs, and DARS outputs across relatively simple, abstract, and physically constrained editing scenarios.

Variant	RISE	GEdit
Curriculum
No Curriculum	18.89	6.87
Static Curriculum	24.56	7.15
Adaptive Curriculum	27.50	7.86
Routing
No Routing	20.05	7.12

Table 2. Ablation on curriculum and routing strategies.

Variant	RISE	GEdit
Planner structure
Free-form Reasoning	23.94	6.98
Modify Only	25.21	7.11
Without Preserve	26.08	7.34
Without Overall	26.42	7.51
Without Tips	26.87	7.69

Table 3. Ablation on planner structure and reward composition.

Setting	Accuracy	Macro-F1	AUROC
Planner vs. Renderer	86.0	85.8	0.930
Planner vs. Mixed	84.7	84.1	0.918
Renderer vs. Mixed	85.3	84.9	0.923

Table 4. Routing-signal discrimination against majority-voted GPT-5 pseudo-labels.

Figure S1. Five-panel schematic of checklist-based prefix-gated planner reward on a sequence-completion edit. Panels A–B define the shared input, checklist, and structured plan; Panels C–E illustrate Failure A, Failure B, and Success under the same scoring and gating rules. Detailed interpretation is provided in Sec. 2.4 . A five-panel schematic for prefix-gated planner reward on a sequence-completion editing example. The first panel shows the source sequence and raw instruction. The second panel lists the modify, preserve, overall, and tips checklists. The remaining three panels show simulated Failure A, Failure B, and Success prompts, their edited sequences, checklist hit counts, scores, gate outcomes, and final rewards.

Category	Hyperparameter	Value
VLM Policy	Base model	Qwen3-VL-4B-Instruct
	Optimizer	AdamW
	Learning rate	$2\times 10^{-6}$
	Plans per input ( $M$ )	4
	Total rollouts per input ( $M\times K$ )	16
	Global update batch size	256

Table S1. Training recipe summary.

Model	Factual Knowledge				Conceptual Knowledge			Procedural Knowledge			Overall $\uparrow$
Model	Attribute Perception $\uparrow$	Spatial Perception $\uparrow$	Temporal Perception $\uparrow$	Average Score $\uparrow$	Social Science $\uparrow$	Natural Science $\uparrow$	Average Score $\uparrow$	Logical Reasoning $\uparrow$	Instruction Decomposition $\uparrow$	Average Score $\uparrow$	Overall $\uparrow$
Other baselines
ThinkGen	64.03	55.17	56.31	59.57	66.00	63.19	63.86	38.04	64.83	49.52	59.57
UniREdit	61.10	66.75	58.45	62.42	66.20	63.04	63.80	53.08	54.61	53.74	61.02
PromptRL	67.85	64.83	79.17	69.04	58.65	57.39	57.69	51.38	67.29	58.24	61.24
Step1X-Edit-v1p2	69.67	64.33	80.18	70.21	63.50	60.62	61.32	49.75	62.67	55.29	62.58

Table S2. Fine-grained KRIS-Bench results. We use the official GPT-4.1-based evaluation protocol. KRIS-Bench evaluates edited results with four dimensions: visual consistency, visual quality, instruction following, and knowledge plausibility, where the last dimension is used only for knowledge-intensive subsets such as Social Science, Natural Science, and Logical Reasoning. The raw judge outputs are defined on a 1–5 scale, while the benchmark reports normalized percentage scores with maximum 100. Higher is better for every metric. All values are reported with two decimal places.

Method	Temporal $\uparrow$	Causal $\uparrow$	Spatial $\uparrow$	Logical $\uparrow$	Overall $\uparrow$
Other baselines
ThinkGen	15.29	16.67	7.00	3.52	10.56
UniREdit	15.29	20.00	14.00	3.53	13.33
PromptRL	3.53	8.89	23.00	2.34	10.00
Step1X-Edit-v1p2	14.12	13.30	13.00	5.88	11.67
UniReason 1.0	16.47	27.78	13.00	2.35	15.00

Table S3. Fine-grained RISE-Bench results. We evaluate on RISEBench-360, the 360-sample version of the benchmark, using the official GPT-4.1-based judging pipeline. The benchmark scores each sample along instruction reasoning, appearance consistency, and visual plausibility, and counts a case as solved only when all applicable dimensions receive full marks. The table therefore reports Accuracy (%), i.e., the task success rate, for each reasoning category and for the overall set. Higher is better for every metric.

Method	Add $\uparrow$	Adjust $\uparrow$	Extract $\uparrow$	Replace $\uparrow$	Remove $\uparrow$	Background $\uparrow$	Style $\uparrow$	Hybrid $\uparrow$	Action $\uparrow$	Overall $\uparrow$
Other baselines
ThinkGen	4.20	3.96	3.45	4.35	3.35	4.22	4.91	3.45	4.16	3.97
UniREdit	4.09	3.53	2.27	4.27	3.81	3.83	4.65	2.46	4.37	3.70
PromptRL	4.07	4.19	2.95	4.23	3.67	4.09	4.46	3.04	4.13	3.87
Step1X-Edit-v1p2	4.28	4.40	2.29	4.36	4.17	3.94	4.74	3.61	4.23	4.00
UniReason 1.0	4.18	3.78	2.65	4.50	4.39	4.01	4.73	2.78	4.36	4.06

Table S4. Fine-grained ImgEdit-Bench results. The header enumerates the benchmark’s nine common editing tasks: Add , Remove , Adjust , Replace , Style , Background , Action , Hybrid , and Extract . ImgEdit-Bench evaluates each result with GPT-4.1 on a 1–5 scale from three perspectives: instruction following, editing quality, and detail preservation. Instruction following measures understanding of the prompt and target concept; editing quality measures how accurately the target region is manipulated; and detail preservation measures fidelity on content that should remain unchanged. Because instruction following is foundational and cannot be fully separated from the other two aspects, the editing-quality and detail-preservation scores are upper-bounded by the instruction-following score. The table reports the average score for each edit category, and higher is better for every metric.

Method	Intersection subset			Full set
Method	G_SC $\uparrow$	G_PQ $\uparrow$	G_O $\uparrow$	G_SC $\uparrow$	G_PQ $\uparrow$	G_O $\uparrow$
Other baselines
ThinkGen	7.49	7.80	7.22	7.43	7.76	7.16
UniREdit	7.31	6.96	6.67	7.10	6.89	6.47
PromptRL	7.32	7.60	6.90	7.15	7.58	6.74
Step1X-Edit-v1p2	8.32	7.89	7.73	8.05	7.85	7.47

Table S5. Fine-grained GEdit-Bench-EN results. The header uses the official benchmark notation: G_SC denotes GPT-4.1-based semantic consistency, G_PQ denotes GPT-4.1-based perceptual quality, and G_O denotes the official overall score. Semantic consistency evaluates how well the edited result follows the instruction, while perceptual quality evaluates image naturalness and artifact level; both use a 0–10 scale. “Intersection subset” refers to the subset of test images for which all compared models return valid outputs, whereas “Full set” refers to the complete GEdit-Bench-EN test set. All values are reported with two decimal places.

Method	LP $\uparrow$	LSE $\uparrow$	Reflection $\uparrow$	Refraction $\uparrow$	Deformation $\uparrow$	Causality $\uparrow$	GST $\uparrow$	LST $\uparrow$	Overall $\uparrow$
Other baselines
ThinkGen	64.39	66.34	64.51	65.46	50.06	51.26	68.38	66.34	60.82
UniREdit	61.99	66.17	67.50	54.38	53.11	52.90	65.68	56.83	60.40
PromptRL	56.04	52.24	59.27	41.35	50.42	45.60	52.91	45.67	51.02
Step1X-Edit-v1p2	63.52	58.12	66.61	62.44	53.41	48.76	52.60	51.89	56.15
UniReason 1.0	62.15	63.20	62.73	51.35	52.55	48.84	60.21	54.76	57.30

Table S6. Fine-grained PICA-Bench results under the simple-prompt setting. This setting corresponds to the superficial-prompt protocol in PICA-Bench and is evaluated by GPT-4.1 for instruction-based image editing models. All reported numbers are Accuracy (%). In the header, LP, LSE, GST, and LST denote Light Propagation, Light Source Effects, Global State Transition, and Local State Transition, respectively.

Method	LP $\uparrow$	LSE $\uparrow$	Reflection $\uparrow$	Refraction $\uparrow$	Deformation $\uparrow$	Causality $\uparrow$	GST $\uparrow$	LST $\uparrow$	Overall Score $\uparrow$
Other baselines
ThinkGen	66.17	68.29	64.82	62.63	59.43	58.57	74.48	61.12	65.09
UniREdit	64.34	66.80	67.50	59.77	63.72	62.17	72.81	68.41	66.55
PromptRL	61.20	59.68	63.66	43.02	55.11	62.88	66.96	55.50	60.38
Step1X-Edit-v1p2	58.92	61.60	66.02	49.12	56.68	59.30	61.36	63.91	60.55
UniReason 1.0	59.32	64.85	60.03	49.77	56.47	60.83	69.23	61.09	61.62

Table S7. Fine-grained PICA-Bench results under the explicit-prompt setting. All reported numbers are Accuracy (%). All values are reported with two decimal places.

Method	Main Backbone	Key Structural Characteristics
ThinkRL-Edit	Qwen3-VL-30B-A3B + Qwen-Image-Edit	Checklist-style reward-driven RL with explicit CoT planning and reflection before image-to-image diffusion editing.
ThinkGen	Qwen3-VL-8B-Think + OmniGen2-4B DiT	Alternating GRPO between a reasoning VLM and a DiT generator.
Step1X-Edit-v1p2	Qwen2.5-VL-7B + Step1X-Edit	Multi-round reflection pipeline (up to five rounds) with coupled VLM and editor tuning.
RePlan	Qwen2.5-VL-7B + Qwen-Image-Edit-2511	Region-aware decomposition: an RL-trained VLM predicts boxes and localized prompts for editing.
EditThinker	Qwen3-VL-8B + Qwen-Image-Edit	Up to five rounds of reflection, with reasoning refinement concentrated on the VLM side.
UniReason 1.0	Bagel-14B	World-knowledge-aware prompt enhancement with reflection and consistency control.

Table S8. Detailed baseline architecture summary.

Figure S2. Additional baseline comparisons on challenging edits. The figure adds side-by-side results for several baselines under the same evaluation setting. Supplementary qualitative comparison figure showing additional baseline outputs on challenging image editing tasks, alongside DARS results for the same cases.

Figure S3. Representative failure cases illustrating current limitations. From left to right, the examples highlight failure modes on puzzle completion, dense final-state reasoning in a mechanics-style diagram, precise relative-size control across multiple objects, and maze-path drawing. Together they show that the method remains weaker when the desired target is difficult to specify textually, when the edit depends on tightly coupled multi-step reasoning, or when exact geometric control is required. Failure-case figure showing four representative limitations: incomplete puzzle completion, an incorrect lever final state, inaccurate size normalization across stacked lunch boxes, and an unstable maze solution path.

Figure S4. Additional reasoning-intensive editing examples. The figure covers temporal, spatial, logical, physical, and knowledge-intensive editing cases. Supplementary qualitative figure with additional reasoning-intensive image editing examples, showing source images, instructions, model outputs, and DARS results on more complex reasoning-heavy tasks.

ID	Raw	Modify	Preserve	Overall	Tips
1	Draw what it will look like after 30 seconds in summer.	Show the dry leaf catching fire under the concentrated sunlight from the magnifying glass, with a small flame and a plume of grey smoke rising from the bright focal point on the leaf.	Preserve the surrounding green grass, the hand holding the magnifying glass, the position of the lens, and the overall sunny daylight illumination.	The scene should depict the early stage of combustion in a visually coherent and physically plausible way under strong summer sunlight.	Add a charred, blackened texture around the focal point and ensure the smoke and flame originate naturally from the concentrated light spot on the brown leaf.
2	Draw what it will look like ten seconds later.	Edit the image to depict the scene ten seconds later by removing the suspended water droplets, the central splash pillar, and the concentric ripple rings.	Preserve the background mountains, the tree-covered hills, the cloudy sky, the soft natural lighting, and the original lake setting.	The final image should look calm, smooth, and undisturbed, as if the splash event has fully settled into a serene static scene.	Maintain the original low camera angle, depth of field, and color grading, and ensure the reflections on the still water align naturally with the surrounding landscape.
3	Draw what it will look like after 30 minutes.	Change the scene to show the pot after the milk has been boiling for 30 minutes, with messy frothy milk spills down the black pot and onto the gas stove grate, along with a reduced, thickened, overheated surface inside the pot.	Preserve the shape and material of the pot, the visible gas flame, the stove grate structure, the blurred background, and the original warm lighting and perspective.	The result should convey a realistic long-boiling, overheating situation with coherent interactions between milk, pot, stove, steam, and smoke.	Add bubbly and browned residue along the inner rim, mix darker smoke with the steam, and make the spilled milk follow gravity and pool plausibly on the stove surfaces.
4	The caterpillar wants to find the shortest path to the leaf. Please mark the two shortest paths in the diagram.	Mark the two shortest surface paths from the orange caterpillar at the bottom front corner of the cube to the green leaf on the top face using two distinct overlaid lines.	Preserve the original blue cube, the green leaf, the orange caterpillar, and the white background exactly as they are.	The final image should look like a clean diagrammatic solution that remains geometrically consistent with the cube’s perspective.	Draw one path across the front-left face and top face, and the other across the front-right face and top face, rendering both lines clearly and aligned to the cube surface geometry.
5	Move only two matchsticks on the left side of the equation to make the equation true. Draw the final equation.	Transform the left side of the matchstick equation so the final result reads 3 - 3 = 0 by changing the two left digits accordingly.	Preserve the minus sign, the equals sign, the digit 0 on the right, the white background, and the overall matchstick style.	The final image must show a coherent, mathematically correct, and well-aligned matchstick equation.	Turn the 8 into a 3 by removing the two left vertical matches, turn the 7 into a 3 by adding a middle and bottom horizontal match, and match the existing dark match heads and rectangular shafts.
6	Remove the water from the glass cup.	Remove the water from the glass cup so the glass interior appears empty and dry, and the tennis ball appears without liquid-induced distortion.	Preserve the “HEAD ATP” text, the fuzzy tennis-ball texture, the shape and material of the clear glass cup, and the bright cyan background.	The final result should look like a realistic dry glass container holding the ball naturally at the bottom under the same viewing conditions.	Eliminate optical refraction, magnification, and distortion from the ball, while maintaining the original lighting, shadows, and camera viewpoint.

Table S9. Actual four-slot plan decompositions for representative qualitative cases. Each row lists the raw user instruction together with its Modify , Preserve , Overall , and Tips fields in the same slot schema used throughout the paper.

Figure S5. Additional general editing examples. The figure covers localized modifications, preservation-sensitive edits, semantic scene changes, extraction, and removal cases. Supplementary qualitative figure with additional general image editing examples, complementing the reasoning-intensive cases with more standard editing scenarios and DARS outputs.

Figure S6. System prompt used for GPT-5 failure-attribution annotation in the routing-signal validation study. The raw outputs planner_side , renderer_side , and both are mapped in the paper to planner-dominant , renderer-dominant , and mixed , respectively. A boxed system prompt template for GPT-5 failure attribution in instruction-based image editing, defining planner-side, renderer-side, and both, together with decision rules and output constraints.

Figure S7. Planner-side prompt template used during rollout to rewrite a raw editing instruction into a four-slot plan. The resulting

\mathbf{e}

is the planner output used by the renderer and by planner-side reward scoring. A boxed prompt template for rewriting image editing instructions into a four-slot specification with sections on editing objectives, tagged-field structure, grammatical rules, and editing-specific rules.

Figure S8. Prompt template used in the offline Gemini 3 Pro preprocessing stage to generate the shared slot-aligned checklist

\mathbf{C}(\mathbf{x})

from the source image and user instruction. The template enforces slot exclusivity, cross-slot complementarity, post-render verifiability, and strict binary Yes/No evaluability so that the same pre-generated checklist can be reused across planner reward, renderer reward, hardness estimation, and routing. A boxed prompt template for generating a shared slot-aligned checklist with four question lists for modify, preserve, overall, and tips, together with design constraints and JSON output requirements.

Figure S9. Planner-side single-question prompt for the Modify slot. The prompt evaluates one checklist question as a post-render diagnostic of whether the current Modify slot text functioned as an adequate plan. Two boxed prompt templates for planner-side Modify-slot evaluation: a system prompt defining the judgment rules and a user prompt providing the source image, rendered image, slot text, and checklist question.

Figure S10. Planner-side single-question prompt for the Preserve slot. The prompt evaluates one checklist question as a post-render diagnostic of whether the current Preserve slot text adequately protected unchanged content. Two boxed prompt templates for planner-side Preserve-slot evaluation: a system prompt defining the preservation judgment rules and a user prompt providing the source image, rendered image, slot text, and checklist question.

Figure S11. Planner-side single-question prompt for the Overall slot. The prompt evaluates one checklist question as a post-render diagnostic of whether the current Overall slot text adequately constrained global coherence. Two boxed prompt templates for planner-side Overall-slot evaluation: a system prompt defining the coherence judgment rules and a user prompt providing the source image, rendered image, slot text, and checklist question.

Figure S12. Planner-side single-question prompt for the Tips slot. The prompt evaluates one checklist question as a post-render diagnostic of whether the current Tips slot text provided adequate local implementation guidance. Two boxed prompt templates for planner-side Tips-slot evaluation: a system prompt defining the local-guidance judgment rules and a user prompt providing the source image, rendered image, slot text, and checklist question.

Figure S13. Renderer-side single-question prompt for the Modify slot. The prompt evaluates one checklist question as an execution-scoring query over visible modification quality. Two boxed prompt templates for renderer-side Modify-slot evaluation: a system prompt defining the execution-scoring rules and a user prompt providing the source image, rendered image, slot text, and checklist question.

Figure S14. Renderer-side single-question prompt for the Preserve slot. The prompt evaluates one checklist question as an execution-scoring query over whether unchanged content is actually preserved. Two boxed prompt templates for renderer-side Preserve-slot evaluation: a system prompt defining the preservation scoring rules and a user prompt providing the source image, rendered image, slot text, and checklist question.

Figure S15. Renderer-side single-question prompt for the Overall slot. The prompt evaluates one checklist question as an execution-scoring query over global coherence and realism. Two boxed prompt templates for renderer-side Overall-slot evaluation: a system prompt defining the coherence scoring rules and a user prompt providing the source image, rendered image, slot text, and checklist question.

Figure S16. Renderer-side single-question prompt for the Tips slot. The prompt evaluates one checklist question as an execution-scoring query over local implementation quality. Two boxed prompt templates for renderer-side Tips-slot evaluation: a system prompt defining the local-detail scoring rules and a user prompt providing the source image, rendered image, slot text, and checklist question.

DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing

Abstract

Figures & tables

RL for Image Editing

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing

RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing

Abstract

RL for Image Editing

Explore similar work

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing

RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing