Generative policies have emerged as a promising paradigm for robot learning, combining expressive generative action modeling with scalable imitation learning from large demonstration corpora. However, heterogeneous demonstrations can induce suboptimal action chunks whose errors compound over time, eventually driving the robot into out-of-distribution states from which recovery is difficult. Action verification offers a test-time scaling strategy for mitigating this failure mode by sampling multiple candidate actions and using a verifier to select one for execution. Existing approaches, however, remain temporally myopic and costly to train, evaluating candidates from the current observation alone without accounting for trajectory continuity and often relying on large verifiers and additional expert demonstrations. In this paper, we introduce Temporal Verification (TeV), an efficient temporally aware action verification framework for flow-matching VLAs. TeV first learns a temporal token that summarizes recent observation--action history, enabling candidate chunks to be evaluated as continuations of the execution trajectory rather than as isolated predictions. Conditioned on this token, TeV constructs positive--negative pairs without additional expert demonstrations or preference annotations and trains an energy-based verifier contrastively to assign lower energy to higher-quality, trajectory-consistent action chunks. Beyond post-hoc ranking, TeV further uses the learned energy landscape to guide intermediate flow samples toward lower-energy regions, improving candidates before final selection. Extensive experiments in simulation and real-world settings demonstrate that TeV provides reliably ranks action candidates, improves task success rates, and produces smoother execution trajectories.
Figures & tables
Figure 1 : Paradigm comparison. (a) Conventional action verification selects among multiple sampled candidates at each decision step, relying only on the current observation. (b) Temporal-consistency methods refine the current prediction by using previous action chunks to promote cross-chunk coherence. (c) Temporal Verification integrates action verification with temporal consistency modeling. Conditioned on past observation-action context, the learned temporal verifier guides and selects action chunk candidates that are more consistent with recent execution.
Figure 2 : Illustration of Temporal Verification. (a) Overall pipeline. We encode observation-action history into a temporal token and use it to condition the energy-based contrastive verifier. At each flow-matching integration step, candidate representations are scored by the verifier. The resulting energy scores are used to guide intermediate samples during integration and rank completed chunks after integration. (b) Verifier training process. Expert chunks serve as positives, while temporally mismatched chunks and policy-generated deviations serve as negatives. The verifier is trained to assign positives lower energy than negatives by at least a specified margin.
Method
Adjust Bottle
Pick Bottles
Place Container
Stack Bowls
Place Cup
Open Laptop
Press Stapler
Average
Base
86.0
48.0
86.0
89.0
78.0
75.0
44.0
72.3
Random
85.0
52.0
90.0
88.0
79.0
72.0
50.0
73.7
TE
87.0
43.0
86.0
88.0
82.0
74.0
47.0
72.4
BID
87.0
59.0
87.0
91.0
76.0
77.0
47.0
74.9
TACO
81.0
46.0
87.0
85.0
80.0
62.0
49.0
70.0
TACO ∗
85.0
32.0
85.0
87.0
80.0
67.0
52.0
69.7
Table 2: Performance (%) comparison on RoboTwin2.0 tasks. Best performance in bold .
Figure 4Figure 5
Figure 6 : Illustration of robot kinematics and task progress over time. Left: Average joint velocity and acceleration during interaction with the water cup. Right: Real-world rollouts. The baselines often exhibit abrupt motions and oscillations, leading to water spilling or task failure, whereas our method maintains a steadier trajectory and completes the task without spilling.
By relying on independent couplings from uninformative Gaussian priors, standard diffusion and flow matching models are forced to learn complex, high-cost vector fields to reach the physical action space. Generative models excel at capturing multimodal behaviors for robotic Learning from Demonstration (LfD), but often suffer from high inference cost. This paper introduces Temporal Policy, a generative framework based on stochastic interpolants that formulates action generation as a temporally coupled transport problem. By initializing the generative flow at the robot's recent history, we explicitly couple past states to future action sequences. This data-dependent coupling reduces transport cost and produces straight vector fields. We validate Temporal Policy across visuomotor simulation benchmarks and on a physical Barrett WAM 2x 7DoF teleoperation platform. Our approach reduces transport costs by nearly an order of magnitude compared to noise-initialized baselines, achieving a 19.1 ms inference latency on a single NVIDIA RTX 4080. Crucially, these geometric and computational efficiencies are achieved while matching the success rates of state-of-the-art baselines. This simplified transport geometry bypasses the computational bottleneck of independent Gaussian priors, helping enable high-frequency, closed-loop control. The code is publicly available at https://github.com/dmiller12/TemporalPolicy.
Dylan Miller, Martin Jagersand
Department of Computing Science, University of Alberta, Canada
Robots deployed in the real world should learn from their experience and improve over time. This requires a mechanism of practicing and learning from feedback. In this paper, we propose VERITAS, a generator-verifier framework for generalist robot policies for inference-time policy steering and self-improvement. We use a pre-trained generalist robot policy as a generator'' and pair it with a gradient-free visual verifier'' that evaluates actions at inference time. This framework enables inference-time steering that improves policy performance without additional training. We demonstrate that inference-time verification consistently outperforms vanilla generalists without training on additional demonstration data. Additionally, we demonstrate that the verified rollouts provide effective supervision for offline policy improvement: policies fine-tuned on verified self-generated trajectories achieve consistent performance gains. Notably, we find that post-training with verified rollouts achieves comparable efficiency to expert demonstrations, while requiring no human interventions. Our results highlight inference-time verification as a practical and scalable mechanism for improving robotic policies during deployment.
Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robot control. However, their performance remains fundamentally constrained by the availability of high-quality robot trajectory data. In current robot learning practice, such data are primarily collected through human teleoperation, which is labor-intensive, costly, and difficult to scale. In this paper, we propose RDGen, a sim-to-real reinforcement learning framework for generating high-quality robot demonstrations. Rather than employing reinforcement learning solely as the final control policy, RDGen leverages trained RL policies as a structured trajectory generator. The system consists of a VLM-based task parser that identifies task-relevant objects, a Grounding DINO-based object localizer, and an RL policy transferred from simulation to the real robot. Successful rollouts are then harvested as clean, high-quality demonstrations for downstream VLA training, while the simulation stage further provides a scalable source of additional trajectories at little marginal cost. Experiments on a pick-and-place task demonstrate that the transferred RL policy achieves a high task success rate. Compared with human teleoperation, RDGen produces significantly smoother trajectories and yields superior downstream VLA performance. These results indicate that RL-generated demonstrations can serve as more reliable and consistent supervisory signals for robot policy learning.