SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation

Youqiang Gui; Yuxuan Zhou; Shen Cheng; Xinyang Yuan; Haoqiang Fan; Peng Cheng; Shuaicheng Liu

cs.ROMar 5, 2026

SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation

Authors: Youqiang Gui, Yuxuan Zhou, Shen Cheng, Xinyang Yuan, Haoqiang Fan, Peng Cheng, Shuaicheng Liu

Organizations: Sichuan University · Independent Researcher · Dexmal Inc. · UESTC

Abstract

Imitation Learning (IL) enables robots to acquire manipulation skills from expert demonstrations. Diffusion Policy (DP) models multi-modal expert behaviors but degrades when naively increasing stacked observation horizons, limiting long-horizon manipulation. We propose Self-Evolving Gated Attention (SEGA), a temporal module that maintains a time-evolving latent state via gated attention, enabling efficient recurrent updates that accumulate long-term context into a compact latent representation while filtering irrelevant temporal information. Integrating SEGA into DP yields Self-Evolving Diffusion Policy (SeedPolicy), which resolves the temporal modeling bottleneck and extends the effective temporal horizon with moderate overhead. On the RoboTwin 2.0 benchmark with 50 manipulation tasks, SeedPolicy outperforms DP and other IL baselines. Averaged across both CNN and Transformer backbones, SeedPolicy achieves 36.8% relative improvement in clean settings and 169% relative improvement in randomized challenging settings over the DP. Compared to vision-language-action models such as RDT with 1.2B parameters, SeedPolicy achieves stronger performance in the clean setting with one to two orders of magnitude fewer parameters, demonstrating strong efficiency. These results establish SeedPolicy as a state-of-the-art imitation learning method for long-horizon robotic manipulation. Code is available at: https://github.com/Youqiang-Gui/SeedPolicy.

Figures & tables

Figure 1: Horizon scaling analysis. (a) DP shows a counter-intuitive performance drop as the observation horizon grows, indicating that naive frame stacking fails to scale. (b) Temporal attention can initially improve performance, but scaling it to longer horizons incurs quadratic cost and diminishing returns. (c) In contrast, our approach improves task success by recurrently extending the effective temporal receptive field without increasing the per-step observation window.

Figure 2: Overview of the SeedPolicy framework. The system takes current RGB images and joint poses as input, encoding them via a ResNet Encoder and MLP. The core Self-Evolving Gated Attention (SEGA) module (blue box) recursively updates a time-evolving latent state ( $State\ t$ ) to capture long-term spatiotemporal dependencies while generating enhanced observation features ( $EObs_{t}$ ). These context-rich features are then fed into the Action Expert, a transformer-based diffusion model, to predict a sequence of future actions.

Figure 3: (a) SEGA employs a dual-stream design: the State Update stream (top) evolves the latent state ( $State_{t-1}$ ) by integrating new observations, while the State Retrieval stream (bottom) utilizes historical context to generate enhanced observation features ( $EObs_{t}$ ). (b) The Self-Evolving Gate (SEG) dynamically computes a gating signal directly from the cross-attention logits. It selectively fuses the intermediate evolved state ( $\text{Inter}\cdot S_{t}$ ) with the previous state, ensuring only semantically relevant information is preserved while filtering out noise.

Figure 4: Performance comparison across varying task length. A consistent trend emerges in both architectures: as the task length increases, the performance gap between SeedPolicy and the baseline progressively widens. This validates the architecture-agnostic effectiveness of our approach, demonstrating that the advantage of our explicit temporal modeling becomes increasingly significant in long-horizon scenarios compared to fixed-window baselines.

Method	RDT ( Liu et al. 2024 )	ACT ( Zhao et al. 2023 )	DP ( Chi et al. 2025 )		SeedPolicy
Method	RDT ( Liu et al. 2024 )	ACT ( Zhao et al. 2023 )	Transformer	CNN	Transformer	CNN
Avg. Success (Easy)	34.50%	29.74%	33.10%	28.04%	40.08%	42.76%
Avg. Success (Hard)	13.72%	1.74%	1.44%	0.64%	4.28%	1.54%
# Parameters	1.2 B	80 M	20.61 M	96.80 M	33.36 M	147.26 M

Table 1: Average success rates and parameter counts over 50 tasks. Gray indicates non-comparable VLA results.

Task	Transformer		CNN		Ep.Time	Task	Transformer		CNN		Ep.Time
Task	Baseline	Ours	Baseline	Ours	Ep.Time	Task	Baseline	Ours	Baseline	Ours	Ep.Time
Click Alarmclock	58	61	61	64	2	Place Mouse Pad	0	1	0	1	5
Click Bell	83	85	54	91	2	Place Shoe	12	23	23	26	5
Beat Block Hammer	72	72	42	61	3	Rotate Qrcode	8	23	13	27	5
Grab Roller	84	89	98	93	3	Scan Object	2	9	9	11	5
Lift Pot	74	71	39	80	3	Open Laptop	56	45	49	47	6

Table 2: Per-task performance comparison between Baseline and Ours on 50 tasks in the "clean" setting. Tasks are sorted by episode time ( Ep.Time ) (average duration of expert demonstrations in seconds). Higher success rates are highlighted in bold .

Figure 5: Qualitative failure cases in simulation. We compare the successful execution of SeedPolicy (top row) against representative failure modes of the DP across three tasks: (a) Put Bottles Dustbin ("clean" setting), (b) Handover Mic ("hard" setting), and (c) Grab Roller ("hard" setting). Red circles highlight critical errors, including execution stagnation (getting stuck) and spatial positioning failures (collisions or air grabs). Additional visualizations are provided in the Appendix.

Task	DP	SeedPolicy
Looping Place-Retrieval	14	38
Sequential Picking	10	26
Bottle Handover	16	54
Food Replacement	18	60
Cover and Reveal	16	58

Table 3: Real-world success rates (%) across five tasks.

Figure 6: Qualitative failure analysis in real-world scenarios. We visualize the successful execution of SeedPolicy (top rows) compared to common baseline failures in (a) Looping_Place-Retrieval and (b) Bottle_Handover . Red circles highlight critical errors. Failure Case 1 illustrates execution stagnation caused by Perceptual Aliasing (misinterpreting the returned block as the initial state in (a)) or overfitting to pauses (in (b)). Failure Case 2 demonstrates spatial precision errors (air grabs and collisions) attributed to the lack of explicit depth information. Additional visualization analysis is provided in the Appendix.

Task	DP + ARMT-style	DP + MemoryVLA-style	SeedPolicy
Move Playingcard Away	56	64	68
Turn Switch	50	52	54
Place Object Stand	20	26	28
Dump Bin Bigbin	47	50	52
Place Container Plate	38	51	60
Place Empty Cup	15	30	32

Table 4: Comparison of different memory mechanisms on ten manipulation tasks.

Task	Architecture Design
Task	DP	+ Temp. Att.	+ State	+ Gating
				CA (SeedPolicy)	FFN
Turn Switch (Short)	51	51	51	54	53
Place Empty Cup (Medium)	24	26	28	32	21
Stack Bowls Two (Long)	33	48	65	73	70

Table 5: Component-wise Ablation of SeedPolicy.

Figure 7: Visualization Analysis of the Self-Evolving Gating Mechanism.

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Section	Description
Related Work	An extended review of prior studies related to imitation learning for robotic manipulation and gating mechanisms in sequence modeling.
Hyperparameter Analysis	A comprehensive sensitivity analysis on the key hyperparameters of the Self-Evolving Gated Attention (SEGA) module.
Hardware & Data Collection and Processing	Detailed specifications of the hardware configurations (DOS-W1) and the data collection and processing pipeline used to curate expert demonstrations.
Additional Results	Additional quantitative and qualitative comparisons on both the RoboTwin 2.0 simulation benchmark and real-world robotic setups.
Open-Loop Evaluation	Open-loop evaluations on the training set to verify the model’s capacity and trajectory reconstruction quality.

Appendix

Table 6: Overview of the Appendix Content. This table outlines the supplementary materials provided to support the main paper.

Task	State
Task	30	60	90
Grab Roller	74	89	80
Dump Bin Bigbin	43	52	47
Open Microwave	73	80	79
Handover Mic	80	92	86
Stack Bowls Two	56	73	73

Appendix

Table 7: Ablation study on latent state sequence length (

N_{s}

). We report the success rates (%) on six representative tasks from RoboTwin 2.0. The results demonstrate that

N_{s}=60

achieves superior performance while maintaining a smaller parameter size compared to

N_{s}=90

Task	Network Depth
Task	2	4	6	8
Scan Object	3	2	9	2
Beat Block Hammer	56	35	72	47
Move Can Pot	59	63	71	52
Dump Bin Bigbin	44	43	52	44
Handover Mic	83	77	92	86

Appendix

Table 8: Ablation study on the depth of attention blocks. We report the success rate (%) on seven representative tasks. The model achieves the best balance and performance at depth 6.

Optimization & Training
Hyperparameter	SeedPolicy-Transformer	SeedPolicy-CNN
Optimizer	AdamW	AdamW
Learning Rate	$1\times 10^{-4}$	$1\times 10^{-4}$
LR Scheduler	Cosine Decay	Cosine Decay
LR Warmup Steps	500	500
Batch Size	128	128

Appendix

Table 9: Hyperparameter configurations for SeedPolicy. We report the settings for both Transformer and CNN backbones used in our experiments.

Component	Parameter	Value
Dual Arms	Degrees of Freedom (DoF)	$2\times(6\text{ Arm}+1\text{ Gripper})$
	Payload Capacity	1.5 kg / arm
	Working Radius	647 mm
	Repeatability	$\pm 0.1$ mm
Mobile Chassis	Drive Type	Differential Drive
	Dimensions ( $L\times W$ )	$700\times 620$ mm

Appendix

Table 10: Hardware Specifications of the DOS-W1 Platform. The system integrates dual 7-DoF manipulators with a high-payload differential mobile base, featuring an adjustable lift mechanism for versatile workspace adaptation.

Figure 8: The DOS-W1 Mobile Manipulation Platform. As illustrated, the system integrates dual 7-DoF robotic arms with a differential drive mobile chassis and a vertical lift mechanism. A front-view RGB camera is mounted on the mast for visual perception.

Task	Transformer		CNN		Ep.Time	Task	Transformer		CNN		Ep.Time
Task	Baseline	Ours	Baseline	Ours	Ep.Time	Task	Baseline	Ours	Baseline	Ours	Ep.Time
Click Alarmclock	4	6	5	10	2	Place Mouse Pad	0	0	0	0	5
Click Bell	1	1	0	3	2	Place Shoe	0	0	0	0	5
Beat Block Hammer	0	9	0	0	3	Rotate Qrcode	1	1	0	0	5
Grab Roller	0	51	0	0	3	Scan Object	0	0	0	0	5
Lift Pot	1	5	0	1	3	Open Laptop	2	3	0	1	6

Appendix

Table 11: Per-task performance comparison between Baseline and Ours on 50 tasks in the "hard" setting. Tasks are sorted by episode time ( Ep.Time ) (average duration of expert demonstrations in seconds). Higher success rates are highlighted in bold .

Task	DP	DP+State	SeedPolicy
		+FFN gate	(Ours)
Turn Switch	12	30	35
Place Empty Cup	0	3	6
Stack Bowls Two	0	18	25

Appendix

Table 12: Success rates (%) of models trained and evaluated in the “Hard” setting.

Task	50 Demos	100 Demos	200 Demos
Turn Switch	54	55	57
Place Empty Cup	32	67	87
Stack Bowls Two	73	91	94

Appendix

Table 13: Success rates (%) of SeedPolicy under varying numbers of expert demonstrations.

Task	DP	ACT	$\pi_{0.5}$	SeedPolicy
Swap Blocks	11	2	24	26
Cover Blocks	0	0	0	15
Battery Try	9	19	16	33

Appendix

Table 14: Success rate (%) comparison on three minute-level manipulation tasks.

Task	DP	ACT	Ours-Img	Ours-Voxel
Coffee D2	26	33	80	79
Kitchen D1	50	61	83	89
Mug Cleanup D1	23	31	76	77

Appendix

Table 15: Success rate (%) comparison on MimicGen. Img and Voxel denote image-based and voxel-based observation modalities, respectively.

Figure 9: More qualitative visualization of failure cases in simulation. We compare the successful execution of SeedPolicy (top row) against representative failure modes of the DP across three tasks: (a) Stack Bowls Three ("clean" setting), (b) Stack Blocks Two ("clean" setting), and (c) Shake Bottle ("hard" setting). Red circles highlight critical errors, including execution stagnation (getting stuck) and spatial positioning failures (collisions or air grabs).

Figure 10: More qualitative failure analysis in real-world scenarios. We visualize the successful execution of SeedPolicy (top rows) compared to common baseline failures in Sequential_Picking . Red circles highlight critical errors. Failure Case 1 illustrates execution stagnation caused by Perceptual Aliasing (misinterpreting the placed block as the initial state). Failure Case 2 demonstrates spatial precision errors (air grabs) attributed to the lack of explicit depth information.

Task	RDT ( Liu et al. 2024 )	MemoryVLA ( Shi et al. 2026 )	$\pi_{0.5}$ ( Black et al. 2025 )	SeedVLA
Turn Switch	35	40	42	50
Handover Mic	90	69	58	91
Put Object Cabinet	33	38	54	60
Stack Bowls Two	76	81	93	94
Blocks Ranking Size	0	27	36	45

Appendix

Table 16: Compatibility study on RoboTwin 2.0 with VLA-based policies.

Backbone	Wins	Losses	Ties	Two-sided $p$ -value
Transformer	38	5	7	$2.5\times 10^{-7}$
CNN	41	6	3	$1.8\times 10^{-7}$

Appendix

Table 17: Statistical significance analysis on RoboTwin 2.0 clean-setting tasks. We perform a paired two-sided exact sign test over per-task success rates between SeedPolicy and the corresponding DP baseline. Ties are excluded when computing the p-value.

Explore similar work

ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision
Dec 17, 2025Wenlong Xia, Jinhao Zhang, Ce Zhang +6Robot Skill Learning Visuomotor Policy Learning
[cs.RO]
DSSP: Diffusion State Space Policy with Full-History Encoding
May 14, 2026Zhiyuan Guan, Jianshu Hu, Han Fang +5Long-Horizon Robotic Manipulation Diffusion Policy
Shanghai Jiao Tong University
SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation
Jul 13, 2026Haidong Cao, Wenjun Cao, Quanhao Li +5Long-Horizon Robotic Manipulation Visuomotor Policy Learning
Institute of Trustworthy Embodied AI, Fudan University, China · Shanghai Key Laboratory of Multimodal Embodied AI, China

Dec 17, 2025J/K move · Enter open · S save

ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision

Wenlong Xia, Jinhao Zhang, Ce Zhang, Yaojia Wang+5

[cs.RO]

Robot Skill Learning Visuomotor Policy Learning Diffusion Policy Robotic Manipulation Robot Imitation Learning

Open paper AskPDF arXiv

Vision-based imitation learning has enabled impressive robotic manipulation skills, but action imitation alone provides limited supervision of the geometric consequences of robot behavior. To address this limitation, we introduce Implicit Scene Supervision (ISS) Policy, a 3D visuomotor diffusion policy with a DiT backbone that predicts continuous action sequences from point-cloud observations. ISS augments action diffusion with a supervised robot motion predictor that maps generated actions and robot-state context to end-effector motion, and then uses the predicted motion together with gripper intent to forecast future point-cloud representations. By explicitly modeling the intermediate transition from action to robot motion, ISS encourages the policy to capture how its actions affect the surrounding 3D scene. We further introduce asymmetric gradient routing to separate direct motion regression from scene-level policy supervision, together with a change-balanced objective that accounts for variations in scene-change magnitude. These auxiliary objectives provide dynamics-aware geometric supervision using only expert demonstrations, without requiring additional annotations or auxiliary modules at inference time. ISS Policy achieves state-of-the-art performance on single-arm manipulation tasks in MetaWorld and dexterous manipulation tasks in Adroit, while real-world dual-arm experiments further demonstrate its effectiveness on physical robotic manipulation. The resulting framework preserves the scalable DiT backbone and standard diffusion-policy control interface. Code and videos will be released.

Abstract

Explore similar work

ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision

DSSP: Diffusion State Space Policy with Full-History Encoding

SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation