- Rating
- 2(+1)
- Confidence
- 3(+1)
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2(+1)
Read review
Paper summary
This paper proposes FIGSTRUCT, an agentic framework for scientific figure redesign and editable SVG reconstruction. It integrates multimodal figure understanding, design-reference retrieval, image generation, SVG reconstruction, object hierarchy construction, localized correction, and global refinement. The key idea is an object hierarchy over SVG elements: higher-level groups provide diagnostic context, while object bindings specify editable regions. This hierarchy is maintained throughout iterative correction, enabling localized repairs without altering unrelated figure parts.
Critical strengths
-
Generating editable scientific figures is a meaningful problem beyond conventional image generation. Balancing visual quality and editability is hard, and the paper addresses a real researcher workflow bottleneck.
-
Using an object hierarchy as an intermediate representation is reasonable: separating diagnostic context from edit scope enables iterative SVG correction without regenerating the whole figure.
Critical weaknesses
- The framework combines existing ideas—multimodal understanding, retrieval-augmented planning, image generation, iterative self-correction, vector graphics reconstruction, and structured editing. The main technical contribution appears to be the object hierarchy for SVG correction, yet the paper does not establish why this representation fundamentally differs from existing structured graphics representations (e.g., SVG DOM editing, programmatic vector representations, or other hierarchical editing frameworks). Ablations show that removing components hurts performance, but do not isolate whether the object hierarchy itself provides unique benefits over simpler structured editing. A stronger evaluation would compare alternative intermediate representations under the same generation and correction pipeline.
- Scientific figure redesign is not merely visual improvement; it must preserve scientific meaning, including entities, relationships, causal flows, and methodological structures. Although the paper introduces fidelity metrics (text, unit, relation, order preservation), these rely substantially on model-based annotation. It remains unclear whether redesigned figures preserve the original authors' intended scientific interpretation. For example, a cleaner diagram may still introduce subtle semantic changes in connector direction, module dependency, or hierarchy interpretation. Domain-expert human evaluation would provide stronger evidence that the system improves scientific communication rather than only visual appearance.
- The benchmark comprises 150 manually redrawn figures with preserved textual and logical structures. While controlled, it may not reflect real-world workflows, where researchers often work with incomplete drafts, PowerPoint figures, LaTeX/TikZ sources, low-resolution screenshots, or inconsistent/ambiguous content. The current benchmark is closer to controlled redesign/beautification than general scientific figure editing. More diverse real-world inputs would strengthen claims of general applicability.
- The paper emphasizes low API expenditure, but the default configuration relies on local inference with Gemma-4 31B on two H100 GPUs. API cost alone therefore does not represent true computational expense. A complete analysis should include GPU inference cost, hardware requirements, energy consumption, and total wall-clock cost. The reported runtime also suggests the system is computationally expensive, which warrants more careful discussion.
Questions for authors
-
The paper would benefit from a clearer distinction between scientific figure generation, figure redesign, and SVG reconstruction, as these tasks have different evaluation criteria.
-
The contribution of Global Refinement appears significant in the ablation study. The authors should clarify whether the main gains come from the hierarchy-guided correction mechanism or from the final refinement stage.
-
The benchmark size (150 figures) is relatively small considering the diversity of scientific visualization styles.
-
The paper should discuss failure cases more extensively, especially cases where the system modifies scientific content or introduces unsupported visual elements.
6 comments
(2/5) Response to Reviewer jMxp
Q2. Hierarchy-Guided Correction and Global Refinement
Q2: The contribution of Global Refinement appears significant in the ablation study. The authors should clarify whether the main gains come from the hierarchy-guided correction mechanism or from the final refinement stage.
A: Global Refinement is important in the submitted implementation. The new paired control and sequential component analysis also support a contribution from structured correction.
Direct + Luna control. We reused the same 150 Direct Gemma-4 SVG outputs that scored 77.88 in the submitted Table 7. Each received one GPT-5.6 Luna global-refinement call. The style-reference image was produced by GPT image generation from an agent-prepared prompt informed by retrieved design references. Thus, the before-and-after comparison starts from the same Direct outputs.
| Configuration | Composite quality | Source |
|---|---|---|
| Direct Gemma-4 | 77.88 | Submitted Table 7 |
| Direct Gemma-4 + one Luna refinement | 79.23 | New paired control |
| FigStruct without Global Refinement | 75.98 | Mean of the three metrics in submitted Table 4 |
| Full FigStruct with Gemma-4 | 85.47 | Submitted Table 7 |
One Luna call improves Direct by 1.35 points. Full FigStruct remains 6.24 points higher. We also agree with the observation about the original ablation: without Global Refinement, the submitted pipeline scores 75.98, below Direct at 77.88. Global Refinement therefore plays an important role in that implementation. The new control shows that adding this call directly to an unstructured output does not recover the full result.
On inspecting the outputs, we found that Direct SVGs often lack clear semantic groups. Refinement then requires interpreting and reorganizing a large amount of code. This provides a possible explanation for the limited gain from a single refinement call.
Sequential component analysis in the optimized implementation. During review, we simplified redundant workflow steps while retaining the object-hierarchy mechanism, reconciliation logic, and evaluation prompts. We evaluated this implementation on 150 generated reference images, adding Region Localization, SVG Structure Conversion, and Global Refinement in that order. Global Refinement still uses one Luna call.
| Cumulative configuration | Composite quality | Increment | Share of total gain |
|---|---|---|---|
| Starting configuration | 78.16 | n/a | n/a |
| + Region Localization | 80.35 | +2.19 | 27.14% |
| + SVG Structure Conversion | 85.45 | +5.10 | 63.21% |
| + Global Refinement | 86.23 | +0.78 | 9.65% |
| Total gain | n/a | +8.07 | 100.00% |
The starting and final scores come from the new evaluation. The intermediate scores and increments shown here are reconstructed from the total gain of 8.07 and the recorded contribution percentages, then rounded to two decimal places. For example, the Region Localization increment is 8.07 × 27.14%.
Under this implementation and addition order, the first two components account for 90.35% of the observed gain, and Global Refinement accounts for 9.65%. These are sequential contributions, which depend on the preceding components. They should be interpreted within this implementation. The submitted ablation, round-count comparison, and cost analysis retain their corresponding full-system score of 85.47.
Output inspection suggests that the local controller reconstructs most text, icons, and scientific relationships before final refinement. The final call then improves cross-module spacing, content distribution, connector routing, and use of the canvas. The two stages serve complementary roles: structured correction establishes and repairs editable content, and global refinement improves the overall arrangement.
The four-representation control in W1 keeps global refinement fixed and provides a complementary test of hierarchy organization and maintenance.
(3/5) Response to Reviewer jMxp
W2 & Q4. Expert Evaluation, Scientific Fidelity, and Failure Cases
W2: Scientific figure redesign is not merely visual improvement; it must preserve scientific meaning, including entities, relationships, causal flows, and methodological structures. Although the paper introduces fidelity metrics (text, unit, relation, order preservation), these rely substantially on model-based annotation. It remains unclear whether redesigned figures preserve the original authors' intended scientific interpretation. For example, a cleaner diagram may still introduce subtle semantic changes in connector direction, module dependency, or hierarchy interpretation. Domain-expert human evaluation would provide stronger evidence that the system improves scientific communication rather than only visual appearance.
Q4: The paper should discuss failure cases more extensively, especially cases where the system modifies scientific content or introduces unsupported visual elements.
A: Three computer-science professors with extensive journal-publication experience each rated all 150 outputs before manual editing. Satisfaction rates were 78%, 82%, and 72%. We also document semantic and graphical failures.
Expert assessment. Experts A, B, and C rated overall satisfaction and required revision:
| Expert | Satisfied | Moderately satisfied, substantial revision needed | Unsatisfied, requires redoing | Figures evaluated |
|---|---|---|---|---|
| A | 117 | 24 | 9 | 150 |
| B | 123 | 17 | 10 | 150 |
| C | 108 | 19 | 23 | 150 |
Across 450 ratings of the same 150 outputs, 348 (77.33%) are satisfied, 60 (13.33%) moderately satisfied, and 42 (9.33%) unsatisfied. These judgments assess overall acceptability and revision needs; the fidelity protocol separately examines scientific relationships.
Scientific fidelity. Full-workflow fidelity uses the original input as reference; Table 2 reconstruction uses the shared Step 1.C design image. Under Appendix B.1, the model records item-level evidence, humans review annotations, and code computes scores.
| Metric | What it checks |
|---|---|
| Unit | Preservation of semantic units, including modules, nodes, labels, and formulas |
| Text Accuracy | Correct preservation and semantic ownership of text |
| Relation | Matching endpoints, direction, and relation type, with precision, recall, and F1 |
| Order | Required precedence, stage, numbering, and hierarchical-order constraints |
Text evaluation checks omissions, unsupported additions, duplicates, and semantic ownership. Relations receive credit only when both endpoints, direction, and type are correct. Figure 5 reports:
| Configuration | Relation | Order |
|---|---|---|
| Direct Gemma-4 | 77.80 | 84.39 |
| FigStruct with Gemma-4 | 92.08 | 98.33 |
The gains are 14.28 and 13.94 percentage points. These metrics assess semantics separately from appearance (Appendices B.3.1 and B.5.3).
Post-editing effort. The study covers 50 complex figures and 400 participants. AutoFigure-Edit and Crafter reconstruct the same Step 1.C images. Participants edit in PowerPoint toward a shared design target, with original scientific content overriding any conflicting reference content. Under common acceptance criteria:
| Method | Mean active post-editing time |
|---|---|
| FigStruct with Gemma-4 | 9 min 15 s |
| AutoFigure-Edit | 45 min 19 s |
| Crafter | 58 min 10 s |
Appendix D and Table 8 describe the protocol. Editing time reflects output quality and editability. The new expert ratings precede these human corrections.
Remaining failures. In Section 4.6, FigStruct with GLM gains 6.03 composite points, but Relation and Order fall by 6.69 and 9.44 percentage points. This shows why fidelity dimensions must accompany the composite score. Further final-output failures include:
| Location | Observed error | Implication |
|---|---|---|
| Appendix F.2, Figure 9 | The design image contains a garbled legend. FigStruct infers plausible labels from context. | Improved legibility involves an interpretive change. The corrupted reference alone cannot establish that the inferred meaning is correct. |
| Appendix F.4, Figure 11 | Some network connections are simplified, and a flowchart arrowhead is oversized. | An orderly layout can retain relational and geometric errors. |
| Appendix E.1, Figure 6 | The Terra-controlled output simplifies some icons and retains extra arrowheads at several junctions. | Preserving the main structure can coexist with inaccurate local symbols. |
We will reference these analyses more clearly in the main text. They distinguish visual gains, content preservation, and inference from ambiguity. Appendix G shows successful repairs; the cases above document remaining errors.
(1/5) Response to Reviewer jMxp
Dear Reviewer
jMxp,Thank you for recognizing the importance of editable scientific figures and the value of separating diagnostic context from edit scope. We have added representation controls and expert ratings, and provide fuller cost accounting below.
W1. Object Hierarchies Compared with Simpler Structured Representations
A: A dynamically maintained hierarchy improves on a flat object table by 4.91 to 6.09 composite points across the tested correction-round settings. SVG DOMs already support groups and nesting. Our contribution concerns how semantic relationships and SVG bindings are used and updated during correction.
The hierarchy connects the context needed to diagnose an error with the SVG objects that may be changed. Parent, sibling, and neighboring objects provide spatial and semantic context. The repair plan then specifies either an object-focused edit or a coordinated revision within a target module. After merging the replacement fragment, reconciliation updates object membership and SVG bindings for subsequent review.
For example, moving a module label may require adjusting nearby nodes and connectors. The worker receives the complete target fragment for context, but the correction plan determines the allowed changes. This separates the material needed to understand the problem from the elements selected for repair.
We compared four representations under the same generation and correction pipeline. The flat object table retains one level of module-to-object membership. Objects are assigned directly to a module without finer parent-child nesting, and patches replace the corresponding SVG objects. It therefore retains module grouping and object-level updates.
All four settings use the same 150 figures, initial SVGs, controller, and global-refinement configuration. Hardware is two H100 80 GB GPUs with four complete figure jobs in parallel. Composite scores are on a 0-to-100 scale.
The dynamic hierarchy exceeds the static hierarchy by 3.77 to 6.85 points and the flat table by 4.91 to 6.09 points. The static control tests the value of updating the representation. The flat-table comparison tests finer hierarchical organization and its maintenance beyond module-level grouping.
Appendix G.5 provides an illustrative flight-control example. A first repair jointly adjusts the title, node arrangement, and connections. A later repair addresses only background-border overflow while retaining the corrected content. The representation supports both coordinated edits and a narrower scope when only a small issue remains.
Independent editability. At the default two rounds:
We report these follow-up component scores separately from the component values in submitted Table 4. The dynamic hierarchy improves Object Separability by 3.18 points and SVG Editability by 3.84 points over the static hierarchy. The corresponding gains over no hierarchy are 5.75 and 3.95 points.
Object Separability checks whether a complete required semantic object can be selected or modified independently of other required objects. It carries 50% of the SVG Editability score. Appendices B.4.1 and B.5.5 define the metric and scoring instructions.