$π$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

• URL: http://arxiv.org/abs/2603.02083v1
• Date: Mon, 02 Mar 2026 17:04:49 GMT
• Title: $π$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs
• Authors: Siting Wang, Xiaofeng Wang, Zheng Zhu, Minnan Pei, Xinyu Cui, Cheng Deng, Jian Zhao, Guan Huang, Haifeng Zhang, Jun Wang,
• Abstract summary: Flow-based vision-language-action models excel in embodied control but suffer from intractable likelihoods during multi-step sampling.<n>We propose textbftextit$boldsymbol$-StepNFT (Step-wise Negative-aware Fine-Tuning), a critic-and-likelihood-free framework that requires only a single forward pass per optimization step.
• Score: 64.60188746073904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow-based vision-language-action (VLA) models excel in embodied control but suffer from intractable likelihoods during multi-step sampling, hindering online reinforcement learning. We propose \textbf{\textit{$\boldsymbolπ$-StepNFT}} (Step-wise Negative-aware Fine-Tuning), a critic-and-likelihood-free framework that requires only a single forward pass per optimization step and eliminates auxiliary value networks. We identify that wider exploration spaces necessitate finer-grained, step-wise guidance for alignment. Empirically, $π$-StepNFT unlocks latent potential on LIBERO with competitive few-shot robustness. Moreover, it achieves superior generalization on ManiSkill, outperforming value-based baselines in OOD scenarios by preventing overfitting to multimodal features. This property offers a scalable solution promising for complex real-world applications.

Related papers

• Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training [26.571744733431448]
  Multi-turn LLM agents are pivotal to production systems, spanning customer service automation, e-commerce assistance, and interactive task management.<n>We propose Proximity-based Multi-turn Optimization (ProxMO), a practical and robust framework engineered specifically for the constraints of real-world deployment.
  arXiv  Detail & Related papers  (2026-02-22T15:18:03Z)
• VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation [61.82502719679122]
  We introduce VLNVerse, a benchmark for Versatile, Embodied, Realistic Simulation, and Evaluation.<n>VLNVerse redefines VLN as a scalable, full-stack embodied AI problem.<n>We propose a novel unified multi-task model capable of addressing all tasks within the benchmark.
  arXiv  Detail & Related papers  (2025-12-22T04:27:26Z)
• Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization [13.475938754147625]
  Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks.<n>Agentic Reinforcement Learning (Agentic RL) optimize such models over full tool-interaction trajectories.<n>Two key challenges hinder effectiveness: (1) Sparse, non-instructive rewards, such as binary 0-1 verifiable signals, provide limited guidance for intermediate steps and slow convergence.<n>We propose two complementary techniques: Progressive Reward Shaping (PRS) and Value-based Sampling Policy Optimization (VSPO).
  arXiv  Detail & Related papers  (2025-12-08T11:59:25Z)
• PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning [30.44007644340425]
  We introduce PROPA, a novel framework that integrates Monte Carlo Tree Search (MCTS) with GRPO to generate dense, process-level rewards and optimize reasoning at each intermediate step without human annotations.<n>Across seven benchmarks and four VLM backbones, PROPA consistently outperforms both SFT- and RLVR-based baselines.<n>It achieves up to 17.0% gains on in-domain tasks and 21.0% gains on out-of-domain tasks compared to existing state-of-the-art.
  arXiv  Detail & Related papers  (2025-11-13T13:06:12Z)
• Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs [72.08224879435762]
  textttLearn-to-Ask is a simulator-free framework for learning and deploying proactive dialogue agents.<n>Our approach culminates in the successful deployment of LLMs into a live, large-scale online AI service.
  arXiv  Detail & Related papers  (2025-10-29T12:08:07Z)
• Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models [7.316631310935769]
  Vision-Language-Action (VLA) models have shown strong generalization by leveraging large-scale demonstrations.<n>We propose Flow Policy Optimization (FPO) algorithm, which reformulates importance sampling by leveraging per-sample changes in the conditional flow-matching objective.<n>We evaluate FPO on the LIBERO benchmark and the ALOHA simulation task against supervised, preference-aligned, diffusion-based, autoregressive online RL.
  arXiv  Detail & Related papers  (2025-10-11T03:11:18Z)
• Accelerating RL for LLM Reasoning with Optimal Advantage Regression [52.0792918455501]
  We propose a novel two-stage policy optimization framework that directly approximates the optimal advantage function.<n>$A$*-PO achieves competitive performance across a wide range of mathematical reasoning benchmarks.<n>It reduces training time by up to 2$times$ and peak memory usage by over 30% compared to PPO, GRPO, and REBEL.
  arXiv  Detail & Related papers  (2025-05-27T03:58:50Z)
• UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality [52.49062565901046]
  Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models with human values.<n>Existing approaches struggle to capture the multi-dimensional, distributional nuances of human preferences.<n>We introduce Utility-Conditioned Multi-Objective Alignment (UC-MOA), a novel framework that overcomes these limitations.
  arXiv  Detail & Related papers  (2025-03-10T09:52:42Z)
• Directed Exploration in Reinforcement Learning from Linear Temporal Logic [59.707408697394534]
  Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning.<n>We show that the synthesized reward signal remains fundamentally sparse, making exploration challenging.<n>We show how better exploration can be achieved by further leveraging the specification and casting its corresponding Limit Deterministic B"uchi Automaton (LDBA) as a Markov reward process.
  arXiv  Detail & Related papers  (2024-08-18T14:25:44Z)
• Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization [78.82586283794886]
  $chi2$-Preference Optimization ($chi$PO) is an efficient offline alignment algorithm provably robust to overoptimization.<n>$chi$PO implements the principle of pessimism in the face of uncertainty via regularization.<n>$chi$PO's simplicity and strong guarantees make it the first practical and general-purpose offline alignment algorithm provably robust to overoptimization.
  arXiv  Detail & Related papers  (2024-07-18T11:08:40Z)
• Cost-Effective Online Multi-LLM Selection with Versatile Reward Models [30.892090566736652]
  We introduce the textitC2MAB-V, an online model for selecting and using large language models (LLMs) textitC2MAB-V is specifically tailored for various collaborative task types with different reward models. We show that textitC2MAB-V effectively balances performance and cost-efficiency with nine LLMs for three application scenarios.
  arXiv  Detail & Related papers  (2024-05-26T14:38:24Z)

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.