Potential-Guided Flow Matching for Vision-Language-Action Policy Improvement

• URL: http://arxiv.org/abs/2606.04968v1
• Date: Wed, 03 Jun 2026 14:49:35 GMT
• Title: Potential-Guided Flow Matching for Vision-Language-Action Policy Improvement
• Abstract summary: We introduce ForesightFlow, a self-guided flow-matching policy.<n>It augments each generated action chunk with a learned success-potential trajectory.<n>It scores candidate actions, enabling best-of-$K$ inference without an external critic.
• Score: 27.695600755960736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large vision-language-action (VLA) policies are increasingly trained as conditional generative models over action chunks. Yet deployment produces mixed-quality experience-successful demonstrations, partial completions, recoverable mistakes, and failures-that is difficult to use with standard imitation. Full behavior cloning (BC) imitates failures, filtered BC discards useful sub-trajectories, and offline reinforcement learning adds a large critic. We introduce ForesightFlow, a self-guided flow-matching policy that augments each generated action chunk with a learned success-potential trajectory. The same flow proposes and scores candidate actions, enabling best-of-$K$ inference without an external critic. The key issue is that policy improvement and value calibration require different supervision: advantage weighting should emphasize high-quality actions, but applying the same weights to potential coordinates suppresses failure gradients and creates overconfident scores. We address this with decoupled advantage-weighted flow matching, applying exponentiated advantage weights only to action velocities while training potential velocities uniformly. We further derive a one-step boundary estimator for conditional flow matching, allowing advantage computation with a single stop-gradient forward pass. Across five BEHAVIOR-1K simulation tasks and five real-world bimanual tasks, ForesightFlow improves over imitation baselines, matches the strongest separate-critic baseline in simulation success, improves real-world success, and reduces training compute by $38\%$. Ablations show that decoupling prevents value hallucination, the one-step estimator preserves candidate-ranking fidelity, and self-guided sampling improves long-horizon execution.

Related papers

• VIMPO: Value-Implicit Policy Optimization for LLMs [106.88933849641272]
  Group-relative methods such as GRPO avoid training a critic, but typically assign a trajectory-level advantage to every token.<n>Actor-critic methods provide denser learning signals, but require a learned value function with its own training instability.<n>We introduce VIMPO, a critic-free policy optimization method that derives a policy-implied value function from optimality conditions of KL-regularized reinforcement learning.
  arXiv  Detail & Related papers  (2026-06-18T09:44:12Z)
• Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning [50.738952715864116]
  Expressive continuous control policies form the backbone of advances in scaling imitation learning for simulated and real robot control.<n>We propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time.<n> Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks.
  arXiv  Detail & Related papers  (2026-06-09T16:45:57Z)
• LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching [15.922360971421654]
  We propose Latent Action Flow Policy (LAFP) for scalable latent policy learning.<n>LAFP consistently outperforms prior methods on downstream imitation learning tasks.<n>LAFP incurs less than 1x additional inference overhead.
  arXiv  Detail & Related papers  (2026-06-09T07:49:49Z)
• FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization [15.427278126226662]
  FlowPRO is a reward-free, offline reinforced fine-tuning framework for flow-matching policies.<n>We present RPRO, a preference-optimization objective tailored to the flow-matching action head of VLA models.<n>FlowPRO attains the highest success rate, outperforming four representative baselines.
  arXiv  Detail & Related papers  (2026-06-03T21:47:43Z)
• Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation [40.17737666526493]
  We propose PACT, a Preference-calibrated Actor-Critic Training framework.<n>We first design a progress model that learns from human demonstration and identifies suboptimal segments for credit correction.<n>We then build preference pairs to define a counterfactual advantage that penalizes Bellman targets of the identified suboptimal segment.
  arXiv  Detail & Related papers  (2026-06-02T17:38:25Z)
• LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models [13.30873593845724]
  LoopVLA is a recurrent Vision-Language-Action architecture that learns representation refinement, action prediction, and sufficiency estimation.<n>We show that LoopVLA pushes the efficiency-performance frontier of VLA policies, reducing parameters by 45% and improving inference throughput by up to 1.7 times.
  arXiv  Detail & Related papers  (2026-05-11T03:51:22Z)
• CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies [26.36935074374452]
  Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency.<n>We propose CF-VLA, a coarse-to-fine two-stage formulation that restructures action generation into a coarse-to-fine step.<n>We show that our method establishes a strong efficiency-performance frontier under low-NFE (Number of Function Evaluations) regimes.
  arXiv  Detail & Related papers  (2026-04-27T15:51:40Z)
• EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training [69.32453275232662]
  We show that a learned critic can inject estimation noise that exceeds the state signal it captures, increasing rather than reducing advantage variance.<n>We propose Explained Variance Policy Optimization (EVPO), which monitors batch-level EV at each training step and adaptively switches between critic-based and batch-mean advantage estimation.
  arXiv  Detail & Related papers  (2026-04-21T14:07:39Z)
• What Does Flow Matching Bring To TD Learning? [28.717975688380488]
  Flow matching can be effective for scalar Q-value function estimation in reinforcement learning (RL)<n>We show that their success is not explained by distributional RL, as explicitly modeling return distributions can reduce performance.<n>We argue that the use of integration for reading out values and dense velocity supervision at each step of this integration process for training improves TD learning via two mechanisms.
  arXiv  Detail & Related papers  (2026-03-04T17:51:30Z)
• Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment [61.80228667422234]
  VGPO redefines value estimation across both temporal and group dimensions.<n>It transforms the sparse terminal reward into dense, process-aware value estimates.<n>It replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal.
  arXiv  Detail & Related papers  (2025-12-13T16:31:26Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks [69.54774045493227]
  A drawback of adversarial training is the computational overhead introduced by the generation of adversarial examples. We propose to exploit the interior building blocks of the model to improve efficiency. Compared with previous methods, our method not only reduces the training cost but also achieves better model robustness.
  arXiv  Detail & Related papers  (2023-10-24T01:36:20Z)
• Robust Pre-Training by Adversarial Contrastive Learning [120.33706897927391]
  Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness. We improve robustness-aware self-supervised pre-training by learning representations consistent under both data augmentations and adversarial perturbations.
  arXiv  Detail & Related papers  (2020-10-26T04:44:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.