SteerAct: Unlocking Action Models through Few-Shot Temporal Steering
Authors: Kaichen Zhou, Zhiyan Li, Chongkai Gao, Yuhan Wang, Wenlong Huang, Maggie Wang, Fangneng Zhan, Manling Li, Qianqian Wang, Mac Schwager, Zhuang Liu, Li Fei-Fei, Mengyu Wang, Paul Pu Liang
Organizations: Massachusetts Institute of Technology · Harvard University · Stanford University · Imperial College London · Northwestern University · Princeton University
Improving pretrained robot action models at test time from only a few rollouts remains challenging. Activation steering offers a lightweight approach by modifying feature activations while keeping model weights fixed. However, effective steering requires identifying which features to modify and determining the timing and strength of modification. We introduce SteerAct, a few-shot temporal steering framework that uses a shared temporal descriptor of sparse-feature dynamics for offline feature selection and online control. A pretrained sparse autoencoder provides candidate features, and our temporal descriptor summarizes the distribution of local activation-order patterns for each feature, enabling comparisons across rollouts without requiring timestep alignment. Before steering begins (offline), we use successful and failed reference rollouts to select a single task-specific feature whose temporal descriptors best distinguish the two outcomes and construct its reference banks. During each new execution (online), we compare the feature's evolving temporal descriptor with these references to determine when to intervene and how strongly to increase or decrease its activation via a steering coefficient. Using only 24 outcome-labeled rollouts per task, SteerAct improves task success by approximately 10% relative to unsteered models in evaluations spanning π0.5, Fast-WAM, RoboTwin 2.0, DexJoCo, and real-world manipulation, without updating action-model weights. Code and demos are available at: https://steeract.github.io/.
Figures & tables
Figure 1: Steering one feature at the right time. Using just 24 rollouts per task, SteerAct improves robot behavior by steering a single feature activation, without retraining the action model. As the robot acts, SteerAct compares the patterns of how this feature activation changes with patterns from those existing rollouts to decide when to steer and how to steer. (a) Unsteered and steered real-robot executions illustrate how SteerAct improves task completion. (b) SteerAct improves task success across all 18 evaluated RoboTwin 2.0 and DexJoCo tasks with π0.5 . (c) On DexJoCo with π0.5 , SteerAct achieves the highest mean success among the evaluated methods.
Figure 2: Temporal evidence guides when and how to steer. (a) The selected feature’s activation traces compare a successful reference, an unsteered rollout, and rollouts with adaptive steering. (b) The temporal-support score measures whether the observed activation history of current rollout provides sufficient evidence for comparison with patterns from successful and failed reference rollouts. (c) The steering coefficient αt determines the direction and strength of the activation edit; αt=0 indicates no intervention at that decision.
Figure 3: SteerAct overview. Offline, an SAE fitted to frozen-policy activations exposes candidate directions. Outcome-labeled rollouts determine a feature and its success/failure banks of ordinal dynamics. Online, supported failure-like prefixes enter a signed coefficient search; other prefixes retain αt=0 . The selected decoder direction modifies one configured residual stream, after which the frozen policy generates actions.
Figure 4Figure 5
RoboTwin 2.0
DexJoCo
Method
Bottles in Dustbin
Stack Three Blocks
Rank Blocks by Size
Dual Shoes
Dump Bin into Big Bin
Open Microwave
Turn Switch
Mouse Pad
Diverse Bottles
Mean
Hammer Nail
Click Mouse
Pick Bucket
Pinch Tongs
Fold Glasses
Water Plant
Hanoi Bi
Microwave Bi
Photo Bi
Mean
Time ↓ (ms/decision)
Backbone: π0.5
Base
74
72
43
73
89
84
47
62
77
69.0
82
67
83
22
71
92
15
77
52
62.3
207.9
DSRL-SAC
80
78
40
57
49
100
65
71
100
71.1
80
60
70
18
74
96
10
69
47
58.2
3582.7
DrVLA
62
84
60
86
72
91
48
68
72
71.4
85
76
87
26
68
94
15
84
55
65.6
221.6
COAST
62
74
49
75
88
86
40
66
76
68.4
87
75
79
33
69
93
19
74
59
65.3
214.4
Table 1: SteerAct improves success across backbones and manipulation benchmarks. Among the evaluated methods, SteerAct (Enc) achieves the highest mean success in all four benchmark–backbone settings with modest inference overhead. Success rates are reported in percent ( ↑ ); each Mean averages nine tasks. Time reports per-decision inference latency (ms, ↓ ), shared across datasets. Enc/Dec denote encoder-branch/action-expert steering. Gray highlights SteerAct (Enc); bold / underline mark the best/second-best distinct success rates within each backbone, including ties.
Task
Base
COAST
DrVLA
SteerAct Dec
SteerAct Enc
Folding Cloth
33.3%
26.7%
40.0%
36.7%
53.3%
Cup Ping-Pong
40.0%
36.7%
56.7%
43.3%
63.3%
Push Cube
20.0%
0%
23.3%
20.0%
40.0%
Average
31.1%
21.1%
40.0%
33.3%
52.2%
Table 2: SteerAct improves success on all three real-robot tasks. With π0.5 frozen, SteerAct (Enc) achieves the highest success on every evaluated task, reaching 52.2% average success compared with 31.1% for Base and 40.0% for the strongest baseline, DrVLA. Values are success rates (%, ↑ ). Enc/Dec denote encoder-branch/action-expert steering. Gray highlights SteerAct (Enc); bold / underline mark the best/second-best distinct results in each row.
Figure 4: Single-feature steering improves task completion across manipulation settings. Representative unsteered and steered rollouts on RoboTwin 2.0, DexJoCo, and real robots illustrate how SteerAct corrects execution errors and enables successful task completion while keeping the underlying action model frozen.
Method
Base
Marginals
Increments
Events
Autocorr.
Raw NN
Raw DTW
Dec
Enc
Success
69.0
71.1
70.0
70.1
73.9
72.2
71.7
70.9
77.7
Table 3: Ablations on RoboTwin 2.0 with π0.5 . Values are mean success rates (%) across nine tasks. Gray marks the default single-feature Enc variant (24 total source rollouts). Panels (b)–(d) use Enc; (c) counts successful source rollouts only. Full results are in Appendix Table 5 .
Setting
Frozen
Delay 10
Delay 20
Without support gate
Without failure gate
Without gates
Ours
Mean
23.63
24.63
24.88
23.13
29.88
22.38
36.13
Table 4: Mean success rates (%, ↑ ) across eight VLABench tasks, with 200 evaluation episodes per task and setting ( π0.5 with SteerAct(Enc)). Full results are in Appendix Table 6 .
Appendix figures & tables5 assets
Supplementary material from the paper’s appendix.
Appendix
Method / Setting
Put Bottles in Dustbin
Stack Three Blocks
Rank Blocks by Size
Place Dual Shoes
Dump Bin into Big Bin
Open Microwave
Turn Switch
Place Mouse Pad
Pick Diverse Bottles
Mean
(a) Representation and steering ablations
Base
74
72
43
73
89
84
47
62
77
69.0
Marginals
76
76
48
77
88
77
49
67
82
71.1
Increments
78
76
39
78
89
83
43
61
83
70.0
Events
76
78
45
77
89
82
50
54
80
70.1
Autocorrelation
82
83
49
83
93
86
49
56
84
73.9
Appendix
Table 5: Ablations on RoboTwin 2.0 with π0.5 : (a) temporal descriptors, matching rules, feature counts, steering strengths, and intervention sites; (b) total source rollouts; (c) successful source rollouts. (d) feature count and coefficient adaptation. Entries are success rates (%, ↑ ); Mean averages over the nine displayed tasks. Matching controls use Enc and retain the ordinal-based support gate. Gray highlights the full method. Bold / underline mark the best/second-best distinct results per column within each group, including ties.
Method
Painting
Book
Drinking
Chemistry Tube
Poker
Mahjong
Toy
Fruit
Mean
Frozen
17
46
15
47
18
6
7
33
23.63
Delay 10
17
51
22
47
13
13
5
29
24.63
Delay 20
17
44
19
52
16
11
12
28
24.88
Without support gate
15
49
23
49
12
8
5
24
23.13
Without failure gate
13
48
27
53
22
18
25
33
29.88
Without gates
17
43
24
42
22
9
3
19
22.38
Appendix
Table 6: Timing and gating comparisons on VLABench. Success rates (%, ↑ ) use 200 evaluation episodes per task and reported setting; Mean is the task macro-average. Gray highlights maturity-based steering. Bold / underline indicate the best/second-best distinct reported results per column, including ties.
Parameter
Symbol
Value
Support samples
M
500
Support-gate threshold
τm
0.65
Maximum coefficient magnitude
Amax
10
Coefficient grid spacing
δα
0.5
Appendix
Table 7: Shared SteerAct control hyperparameters.
Figure 5: Simulated rollouts on RoboTwin 2.0. Each panel compares the unsteered frozen backbone (top) with SteerAct (bottom) from a matched initial scene; time advances from left to right.
Figure 6: Paired simulated rollouts on RoboTwin 2.0 and DexJoCo (continued). The unsteered and steered rows begin from matched initial scenes, and frames advance from left to right.
Steering robot foundation models (RFMs) toward new task variants or user-preferred behaviors remains challenging, often requiring additional robot demonstrations, task-specific fine-tuning, or long-context conditioning. We present WAM-TTT, a test-time training framework for steering world action models from raw human videos. Rather than treating human videos as trajectories to imitate, WAM-TTT absorbs them into a lightweight adaptive memory inside a frozen WAM through self-supervised video prediction. To make this memory useful for control, we introduce a meta-training stage that aligns human demonstrations with robot behaviors using paired human-robot data and a key--value memory reconstruction objective. At test time, only unlabeled human videos are required to adapt the memory, while the pretrained WAM remains frozen. This enables efficient and reusable steering without robot actions, human-side annotations, or task-specific fine-tuning, while preserving the generalization ability of the foundation model. Extensive experiments show that WAM-TTT consistently outperforms in-context human-video conditioning baselines across diverse manipulation tasks and generalization settings.
Real-world robot learning increasingly relies on heterogeneous data, but demonstrations and rollouts often mix useful progress with stalls, corrections, and suboptimal behavior. Effective policy learning therefore requires frame-level advantages that distinguish reliable local progress from failures and regressions. We propose Self-supervised Temporal Ensemble Advantage Modeling (STEAM), a label-free method that learns such advantages from expert demonstrations. STEAM trains an ensemble of temporal-offset predictors on frame pairs within expert trajectories, using the normalized temporal offset between two frames as a self-supervised signal. Each predictor maps a frame pair to a distribution over temporal offsets, which is converted into a scalar advantage. STEAM then takes the minimum advantage across the ensemble to score mixed-quality rollout data conservatively. Across real-world bimanual towel folding, chip checkout, table clearing, and cola restocking tasks, STEAM identifies stalls, failures, and recoveries. When combined with CFGRL, STEAM achieves the highest policy success rate on all four tasks, averaging 83.5% against 58.8% for the best baseline. Project page: https://rlinf.github.io/steam/.
Zhihao Liu, Qiuyi Gu, Yitao Wang +16
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Zhongguancun Academy +8
We present Token Steering (TS), a method for dynamically steering trajectories generated by an autoregressive vision-language-action (VLA) model through direct intervention in the action-token space. TS injects low-dimensional user inputs into the model's native action-token representation, allowing users to influence trajectory generation without modifying the underlying vision-language model (VLM) architecture. Because TS operates entirely at inference time, it requires no additional training or finetuning. User inputs guide rather than override the pretrained policy, allowing users to influence robot actions while preserving the dexterity, smoothness, and task priors learned by the VLA. We evaluate TS on two household manipulation tasks -- drawer closing after object placement and state-aware object swapping -- and improve success rates from 10.0% to 72.5% and from 16.7% to 93.8%, respectively. By enabling lightweight, intuitive steering over robot foundation models, our interface has the potential to improve human-robot interaction in consumer environments and broaden accessibility for individuals with limited physical control. Project website: https://jasontchan.github.io/token-steering/ .
Jason Chan, Jonathan C. Kao
Department of Computer Science University of California, Los Angeles · Departments of Electrical and Computer Engineering, Computer Science, and Neurobiology University of California, Los Angeles