RFW-A: Agentic Procedural Generation of 400K Articulated Assets over 500 Categories

Yuanbo Lyu; Changjian Pan; Saining Zhang; Yi Yang; Peishuo Li; Zhiheng Li; Jialu Liu; Junhao Chen

cs.CVOct 29, 2026

RFW-A: Agentic Procedural Generation of 400K Articulated Assets over 500 Categories

Authors: Yuanbo Lyu, Changjian Pan, Saining Zhang, Yi Yang, Peishuo Li, Zhiheng Li, Jialu Liu, Junhao Chen,

Organizations: Alibaba Group · Tsinghua University · Peking University · Nanyang Technological University ·

Abstract

High-quality articulated assets are essential for embodied perception, simulation, and manipulation, yet constructing them at scale remains difficult. Manual annotation and procedural modeling require substantial human effort. Recent agentic systems automate asset construction through program synthesis, but repeat costly reasoning and refinement for every new asset. Our key observation is that assets within a category can share construction logic despite variations in structure and appearance. Agentic synthesis and procedural generation are therefore complementary: agents can construct reusable programs, while procedural execution reuses the resulting logic across many samples. We therefore present RFW-A, which combines the two in a new articulated-asset generation paradigm. Starting from existing articulated programs, RFW-A organizes reusable components and their dependencies into category-level generators. Agents test and refine these generators across sampled configurations and motion states. Once constructed and validated, the generators produce diverse assets through procedural execution with no further model calls or token charges. The estimated API cost of generator authoring averages $10.62, amortizing to$ 0.05 per asset over 200 assets, versus $1.24 for the sampled per-asset agentic synthesis baseline. Using RFW-A, we built RFW-A-400K, containing over 400K sim-ready articulated assets across more than 500 categories. Experiments show high structural and kinematic validity and stable execution across physics simulators. Beyond asset validity, training with RFW-A-400K improves part-level articulation estimation on seen and unseen categories, while policies trained in simulation with retrieved and program-edited assets transfer zero-shot to real articulated objects.

Figures & tables

Figure 2: Cabinet families produced by reusable procedural generators. Across cabinet configurations, the generators vary materials, dimensions, door types, drawer layouts, and appearance while preserving shared rules for panel sizing, part placement, and joint attachment.

Figure 3: Comparison of articulated-asset construction paradigms. Manual annotation operates per asset; procedural generation amortizes sampling but requires category-specific generator authoring; and agentic synthesis repeats model inference for each asset. RFW-A uses agentic synthesis to construct a reusable generator for each object family, then produces assets through procedural sampling.

Figure 4: Overview of the RFW-A generator-construction pipeline. Panel (a) shows how agents extract reusable components from source assets and executable programs, organize them into a category blueprint, and compile the blueprint into a generator. Panel (b) shows procedural execution by sampling choices, resolving dependent parameters, and assembling an asset, followed by validation and repair. Panel (c) shows that a released generator produces a family of articulated variants from different seeds, while exposing the joint motion encoded by the generator.

Dataset	Assets	Cats.	Type				Physical Grounding
Dataset	Assets	Cats.	Type	Metric	Texture	F-mat.	Density	$\bm{E}$	$\bm{\nu}$	Friction	$\bm{e}$
PartNet-Mobility	2,347	46	Manual	$\times$	$\triangle$	$\times$	$\times$	$\times$	$\times$	$\times$	$\times$
Infinite Mobility	On-demand	22	Procedural	$\times$	$\triangle$	$\times$	$\times$	$\times$	$\times$	$\times$	$\times$
Infinigen-Articulated	8,226	17	Procedural	$\triangle$	$\checkmark$	$\times$	$\triangle$	$\times$	$\times$	$\triangle$	$\times$
PhysX-Mobility	2,024	45	Manual	$\times$	$\triangle$	$\times$	$\checkmark$	$\checkmark$	$\checkmark$	$\times$	$\times$
Artiverse	3,544	84	Manual	$\times$	$\checkmark$	$\times$	$\checkmark$	$\times$	$\times$	$\times$	$\times$

Table 1: Release-level comparison of articulated-object datasets, their construction types, and available annotations. Cats. denotes categories, Proc. denotes procedural generation, and Metric denotes metric-scale geometry. Physical Grounding groups the physical-property fields (Section 4.2 ):

E

is Young’s modulus,

\nu

is Poisson’s ratio, Friction includes static and dynamic coefficients, and

e

is the coefficient of restitution. F-mat. marks fine-grained material annotation, i.e., material assignments below the articulated-part level.

\checkmark

indicates that a field or resource is included in the released data or documented format,

\triangle

indicates partial or format-dependent availability, and

\times

indicates that it is absent. The RFW-A-400K row follows the release specification and evaluation manifest.

Figure 5: Qualitative comparison of Articraft, LAM, and RFW-A -400K. The three rows are the compared datasets; each row contains four quality dimensions (geometry, part segmentation, motion, and material appearance).

Figure 6: API-cost scaling of reusable category-level generators versus per-asset agentic synthesis. (a) Our mean generator-authoring cost is amortized over

N

assets, while the baseline averages

N

recorded synthesis costs. (b) Our one-time API cost stays fixed, while the baseline accumulates a new charge for each asset.

Figure 7: How a frozen generator’s per-surface material-class identifiers become concrete materials and physical properties at export: each identifier selects a frozen material pool, a seeded draw binds one pool member to the surface, and that material’s physical properties are copied into the asset’s physics record.

Figure 8: Directed 3D editing enabled by agent-generated procedural programs: (a) structural editing, (b) count editing, (c) material editing, and (d) dimensional editing.

Training data	Rest-Pose Segmentation			Articulated Geometry
	mIoU $\uparrow$	gIoU $\uparrow$	PC $\downarrow$	gIoU $\uparrow$	PC $\downarrow$	OC $\downarrow$
In-domain
PM-only	0.60262	0.46364	0.09552	0.44339	0.15760	0.01253
PM+Articraft	0.71442	0.62972	0.05371	0.60164	0.10196	0.00778
PM+ RFW-A -400K	0.78873 (+10.4%)	0.73550 (+16.8%)	0.03501 (+34.8%)	0.70295 (+16.8%)	0.06268 (+38.5%)	0.00661 (+15.0%)
Category OOD

Table 2: Articulation estimation with different training datasets. Bold marks the best result for each metric within each evaluation split.

Figure 9: Qualitative comparison of articulation estimation. Rows show PM-only, PM+Articraft, PM+ RFW-A -400K, and ground truth (GT). Red arrows and circles highlight local differences in supports, attachments, and movable parts.

Setting	Retrieved Asset	Edited Variants	Sim. Demos
Retrieval	1	0	500
Retrieval + 4 Edit	1	4	500
Retrieval + 9 Edit	1	9	500

Table 3: Simulation configurations for robotic manipulation. All settings use exactly 500 simulation demonstrations per task.

Figure 10: Sim-to-real robotic manipulation. Simulation training environments (top) and corresponding real-world evaluations (bottom) across five articulated-object manipulation tasks.

Setting	Cabinet	Folding Chair	Double Door	Toaster	Folding Ruler	Avg.
Retrieval	5/10	7/10	8/10	7/10	4/10	6.2/10
Retrieval + 4 Edit	7/10	7/10	8/10	8/10	6/10	7.2/10
Retrieval + 9 Edit	8/10	8/10	8/10	9/10	7/10	8.0/10

Table 4: Zero-shot sim-to-real manipulation. Real-world successes over 10 trials per task. All settings use the same 500 simulation demonstrations per task.

Appendix figures & tables18 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Scale		Movable joints			Structural variation
Dataset	Assets	Parsed links	Mean	P-90	Multi-joint (%)	Within-cat. var.	nTED
PartNet-Mobility	2,347	16,665	5.10	9	59.86	24.52	0.411
Infinigen-Articulated	8,226	48,427	3.89	9	73.86	2.15	0.393
PhysX-Mobility	2,024	26,016	4.89	7	55.09	14.83	0.354
Artiverse	3,544	28,971	4.60	7	77.65	12.76	0.372
LAM	3,217	18,306	3.00	5	53.59	2.19	0.373

Appendix

Table 5: Dataset scale and structural variation. Joint statistics are computed over successfully parsed assets. Within-category joint-count variance is averaged equally across each source’s categories. nTED is averaged over all pairs of 250 valid trees per source, including cross-category pairs. Bold marks the best value in each ranked column, where a larger value indicates greater scale or structural diversity; mean and P-90 movable-joint counts are descriptive and are not ranked.

Dataset	(a) Validity			(b) Geometry		(c) Simulation
	Full release			Core-200 (%)		Core-200
	Resource resol. $\uparrow$	Non-deg. $\uparrow$	Kinematic pass $\uparrow$	Joint gap P95 $\downarrow$	Axis support $\uparrow$	Import $\uparrow$	DoF mapping $\uparrow$	Stable rollout $\uparrow$	Inertials $\uparrow$
PartNet-Mobility	0.9859	0.9979	0.9928	39.138	57.952	0.420	0.258	0.415	0.000
Infinigen-Articulated	0.9995	0.8053	0.6944	30.223	50.591	0.930	0.903	0.930	0.000
PhysX-Mobility	$\bm{1.0000}$	0.2664	0.5924	45.481	47.427	0.995	0.998	0.990	0.000
Artiverse	0.9997	0.9704	0.9405	37.433	35.673	0.770	0.724	0.770	1.000

Appendix

Table 6: Asset evaluation across three test groups. (a) File and kinematic validity on each complete release. (b) Rest-pose assembly geometry on Core-200. (c) Import, DoF mapping, inertial completeness, and 1-second numerical stability on Core-200. Values in (a) and (c) are fractions; (b) uses percentages. Lower is better for Joint Gap. Bold marks the best value within each column. See Appendix A.13 for the definitions of the geometry metrics and Appendix Table 9 for the motion-sweep collision results.

Dataset	Resource resol. $\uparrow$	Valid tree $\uparrow$	Joint spec. valid $\uparrow$	Collision cov. $\uparrow$	Strict URDF $\uparrow$
PartNet-Mobility	0.9859	$\bm{1.0000}$	0.9979	0.0000	0.0000
Infinigen-Articulated	0.9995	$\bm{1.0000}$	$\bm{1.0000}$	0.0000	0.0000
PhysX-Mobility	$\bm{1.0000}$	$\bm{1.0000}$	$\bm{1.0000}$	0.0000	0.0000
Artiverse	0.9997	0.9949	0.9989	0.9757	0.9715
LAM	0.9714	0.9226	0.9568	0.4597	0.4109
SketchMobility	0.9903	0.9986	0.9996	0.3860	0.3858

Appendix

Table 7: URDF validity on the complete release of each dataset. Strict URDF is the per-asset conjunction of resource resolution, tree validity, joint specification, and collision coverage. All values are fractions; the best result in each column is bold. See Appendix A.11 for the complete criteria.

Dataset	Valid range $\uparrow$	Joint sweep $\uparrow$	Non-deg. $\uparrow$	Joint-level pass $\uparrow$	Asset-level pass $\uparrow$
PartNet-Mobility	0.9960	$\bm{1.0000}$	0.9979	0.9939	0.9928
Infinigen-Articulated	$\bm{1.0000}$	$\bm{1.0000}$	0.8053	0.8053	0.6944
PhysX-Mobility	$\bm{1.0000}$	$\bm{1.0000}$	0.2664	0.2664	0.5924
Artiverse	0.9993	0.9939	0.9704	0.9697	0.9405
LAM	0.9949	0.8604	0.8574	0.8530	0.8775
SketchMobility	0.9998	0.9991	0.8230	0.8229	0.7203

Appendix

Table 8: Kinematic executability on the complete release of each dataset. Joint-level pass evaluates individual declared movable joints; asset-level pass requires every movable joint of an asset to pass. All values are fractions; the best result in each column is bold. See Appendix A.12 for the sweep and denominator rules.

Dataset	Rest-Pose Geometry				Motion Sweep ( $K=9$ )
Dataset	Joint Support $\uparrow$	All-joint Support $\uparrow$	Joint Gap P95 $\downarrow$	Axis Support $\uparrow$	Pose Axis Support $\uparrow$	Collision-free Poses $\uparrow$	Penetr. Growth P95 $\downarrow$
PartNet-Mobility	20.124	15.500	39.138	57.952	48.688	83.023	29.402
Infinigen-Articulated	$\bm{60.344}$	$\bm{42.500}$	30.223	50.591	39.028	76.840	37.200
PhysX-Mobility	13.148	9.000	45.481	47.427	39.754	78.152	36.497
Artiverse	16.657	5.500	37.433	35.673	17.611	84.599	32.763
LAM	21.933	10.500	54.218	32.361	17.623	71.075	43.443

Appendix

Table 9: Geometric support and collision behavior on Core-200. Rest-pose metrics evaluate assembly support, part separation, and axis placement; motion metrics evaluate support retention and additional penetration over nine joint states. All values are percentages. Lower is better for Joint Gap and Penetration Growth; the best result in each column is bold. See Appendix A.13 for definitions.

Dataset	$N$	Import $\uparrow$	DoF mapping $\uparrow$	Complete non-placeholder inertials $\uparrow$	Genesis 10 s simulation validity $\uparrow$	Trajectory coverage $\uparrow$
PartNet-Mobility	200	0.950	0.920	0.000	0.950	0.000
Infinigen-Articulated	200	0.930	0.903	0.000	0.930	0.000
PhysX-Mobility	200	1.000	1.000	0.000	0.990	1.000
Artiverse	200	0.995	0.992	1.000	0.960	0.955
LAM	200	0.875	0.989	0.000	0.870	0.958
SketchMobility	200	0.995	0.990	0.400	0.995	0.801

Appendix

Table 10: Runtime compatibility and physical stability on Core-200. Panel (a1) evaluates import and rollout behavior in Genesis; panel (a2) evaluates free-root center-of-mass stability in Genesis; and panel (b) requires each asset or joint to pass the corresponding test in Genesis, PyBullet, MuJoCo, and Isaac Sim. All reported rates are fractions.

	Genesis			PyBullet			MuJoCo			Isaac Sim
Dataset	Imp. $\uparrow$	DoF $\uparrow$	Stable $\uparrow$	Imp. $\uparrow$	DoF $\uparrow$	Stable $\uparrow$	Imp. $\uparrow$	DoF $\uparrow$	Stable $\uparrow$	Imp. $\uparrow$	DoF $\uparrow$	Stable $\uparrow$
PartNet-Mobility	0.950	0.920	0.945	0.985	0.994	0.985	0.420	0.258	0.420	0.975	0.984	0.970
Infinigen-Articulated	0.930	0.903	0.930	1.000	1.000	1.000	0.995	0.995	0.995	1.000	1.000	1.000
PhysX-Mobility	1.000	1.000	0.995	1.000	1.000	0.995	1.000	1.000	0.995	0.995	0.998	0.990
Artiverse	0.995	0.992	0.960	1.000	1.000	1.000	0.850	0.855	0.845	0.915	0.839	0.915
LAM	0.875	0.989	0.870	0.880	0.994	0.880	0.440	0.546	0.420	0.920	1.000	0.895

Appendix

Table 11: Per-engine cross-simulator rates on Core-200: native import success, canonical DoF mapping (joint-level), and passive stable rollout (asset-level), each evaluated independently per engine. The main-paper panel (b) reports the per-asset and per-joint intersection across all four engines, not an average of these per-engine rates.

Dataset	Classes	Renders	Metric $N$	DINOv2 Top-1 $\uparrow$	DINOv2 Top-4 $\uparrow$	DINOv2 silh. $\uparrow$	CLIP Top-1 $\uparrow$	CLIP Top-4 $\uparrow$	CLIP silh. $\uparrow$
PartNet-Mobility	46	230	230	0.696	0.567	0.196	0.552	0.365	0.056
Artiverse	84	368	363	0.716	0.604	0.233	0.540	$\bm{0.395}$	$\bm{0.074}$
LAM	660	1,279	860	0.226	0.149	-0.301	0.152	0.113	-0.442
Articraft	244	1,193	1,187	0.530	0.413	0.073	0.405	0.266	-0.051
RFW-A-400K (Ours)	531	2,655	2,655	$\bm{0.881}$	$\bm{0.704}$	$\bm{0.289}$	$\bm{0.592}$	0.373	0.064

Appendix

Table 12: Feature-space class consistency under standardized Blender rendering using all successfully rendered assets. Classes and renders include every available class and image; metric

N

excludes only images from singleton classes when a positive same-class pair is required. Top-1 and Top-4 are the same-class fractions among the nearest one and four neighbors, respectively. The cosine silhouette is

(b_{i}-a_{i})/\max(a_{i},b_{i})

over L2-normalized features. The best value in each metric column is bold.

Figure 11: Joint all-available t-SNE overviews in DINOv2-base (left) and CLIP ViT-B/32 (right) feature spaces. Within each encoder, panels use that encoder’s joint embedding coordinates and axis limits; the two encoders are embedded separately. Colors identify datasets ( RFW-A uses larger outlined markers); all renders, including classes with fewer than five renders, are shown.

Figure 12: All-available feature-space metrics reported in Table 12 . Singleton classes are excluded only from metrics requiring a positive same-class pair; triangles mark the best value within each encoder.

Category	PM	Articraft	RFW-A (new)	Total
Dishwasher	4	4	20	28
Oven	1	11	20	32
Refrigerator	4	12	20	36
Storage furniture	55	11	20	86
Table	9	17	20	46
Washing machine	1	6	20	27

Appendix

Table 13: Category and source composition of the in-domain evaluation split. The added objects belong to the same six categories as the original PartNet-Mobility evaluation split. All three models are evaluated on the complete combined split with equal weight per object.

Training data	Rest-Pose Segmentation			Articulated Geometry
Training data	mIoU $\uparrow$	gIoU $\uparrow$	PC $\downarrow$	gIoU $\uparrow$	PC $\downarrow$	OC $\downarrow$
PM-only	0.79658	0.75910	0.02554	0.73732	0.09812	0.01114
PM+Articraft	0.77070	0.73300	0.02276	0.70978	0.09562	0.01232
PM+ RFW-A -400K	0.78706	0.74752	0.02442	0.72360	0.08508	0.01028

Appendix

Table 14: Articulation estimation on the original PartNet-Mobility evaluation split using the three 150K checkpoints. Results average three training seeds

\times

five evaluation seeds; bold marks the best result. This original split contains 55 storage-furniture objects and 19 objects across the other five categories.

Variant	Mean Judge	Strict Valid	Avg. Iter.	Est. Cost ($)
w/o Component Extraction	0.500	35/108	9.33	3.80
w/o Structural Blueprint	0.401	72/108	11.33	3.73
w/o Validation & Repair	0.241	0/108	0.00	0.83
RFW-A (full)	0.580	108/108	8.00	6.73

Appendix

Table 15: Aggregate generator-component ablation outcomes across flip_phone , microscope , and folding_chair . Mean Judge and Avg. Iter. are category means; Strict Valid reports pooled counts.

Variant	Geometry	Aesthetics	Semantic	Judge
w/o Component Extraction	5.17	4.83	6.50	0.500
w/o Structural Blueprint	4.67	3.83	5.33	0.401
w/o Validation & Repair	2.42	2.83	3.25	0.241
RFW-A (full)	6.25	5.42	7.00	0.580

Appendix

Table 16: Mean component scores across flip_phone , microscope , and folding_chair for the same ablations. Each category receives equal weight; higher is better and bold marks the best mean in each column.

Figure 18: Qualitative comparison of generator-component ablations. Rows show (a) flip phone, (b) microscope, and (c) folding chair. From left to right, columns compare full RFW-A with variants removing Component Extraction, Structural Blueprint, and Validation & Repair, respectively. Quantitative results are reported in Tables 15 and 16 . The panels are qualitative visual examples; mechanical validity is measured by the strict-validity probes in these tables.

Figure 19: Cabinet generator families. Each panel shows assets sampled from one reusable procedural cabinet generator: (top left) a cabinet generator with drawers, (top right) a cabinet generator with drawers and doors, (bottom left) a cabinet generator with doors, and (bottom right) the hutch cabinet generator of Figure 2 , whose row labeled Original reproduces the reference asset; all other rows and columns are generated variants. Within each panel, rows vary component choices, materials, drawer and door layouts, and appearance while the generators preserve shared rules for panel sizing, part placement, and joint attachment.

Articulated 3D Asset Generation

See all 20 papers

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
May 14, 2026Matt Zhou, Ruining Li, Xiaoyang Lyu +63D Asset Generation LLM-Based Program Synthesis
University of Cambridge · University of Oxford · Nanyang Technological University
PAct: Part-Decomposed Single-View Articulated Object Generation
Feb 16, 2026Qingming Liu, Xinyue Yao, Shuyuan Zhang +4Articulated 3D Asset Generation 3D Asset Generation
The Chinese University of Hong Kong, Shenzhen, China · DexForce Technology, China
AffordCraft: Scalable Construction of Task-Ready Simulation Assets from Single Images
Oct 5, 2026Haoyun Yang, Xueyang Zhou, Ziyi Xie +1Articulated Object Reconstruction Robotics Simulation
College of AI, Tsinghua University · School of Computer Science, Chongqing University · School of Cyber Science and Engineering, Huazhong University of Science and Technology +1

May 14, 2026J/K move · Enter open · S save

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation

Matt Zhou, Ruining Li, Xiaoyang Lyu, Zhaomou Song+5

University of Cambridge · University of Oxford · Nanyang Technological University

3D Asset Generation LLM-Based Program Synthesis Synthetic Data Generation for Robotics Articulated 3D Asset Generation

Open paper AskPDF arXiv

A bottleneck in learning to understand articulated 3D objects is the lack of large and diverse datasets. In this paper, we propose to leverage large language models (LLMs) to close this gap and generate articulated assets at scale. We reduce the problem of generating an articulated 3D asset to that of writing a program that builds it. We then introduce a new agentic system, Articraft, that writes such programs automatically. We design a programmatic interface and harness to help the LLM do so effectively. The LLM writes code against a domain-specific SDK for defining parts, composing geometry, specifying joints, and writing tests to validate the resulting assets. The harness exposes a restricted workspace and interface to the LLM, validates the resulting assets, and returns structured feedback. In this way, the LLM is not distracted by details such as authoring a URDF file or managing a complex software environment. We show that this produces higher-quality assets than both state-of-the-art articulated-asset generators and general-purpose coding agents. Using Articraft, we build Articraft-10K, a curated dataset of over 10K articulated assets spanning 245 categories, and show its utility both for training models of articulated assets and in downstream applications such as robotics simulation and virtual reality.

Abstract

Articulated 3D Asset Generation

Explore similar work

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation

PAct: Part-Decomposed Single-View Articulated Object Generation

AffordCraft: Scalable Construction of Task-Ready Simulation Assets from Single Images