arXiv AI

Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine Tuning

arXiv Machine Learning
Sep 17

Reinforcement Learning for Real-Time Vision-Language-Action Policies

The paper presents Real‑Time EXPO‑FT, a reinforcement learning framework that fine‑tunes large Vision‑Language‑Action models for real‑time robotic control. It separates slow, expressive action generation from fast, reactive edits, allowing a lightweight policy to adjust actions based on the latest observation. Experiments on the Kinetix benchmark and four dynamic real‑world tasks show that Real‑Time EXPO‑FT achieves superior performance, improving policy success rates from 42% to 97% with only ten minutes of online data and no human intervention.

By Perry Dong, Kuo-Han Hung, Dorsa Sadigh, Chelsea Finn
arXiv AI
Sep 24

BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models

arXiv:2609.27450v1 Announce Type: cross Abstract: Vision-language-action (VLA) models handle long-horizon manipulation, yet success hinges on a few precision-critical phases where millimeter-scale er...

By Weihui Zhao, Xiaohan Yan, Zunian Wan, Xuan Du, Zhaozhan Chi, Jianbo Mao, Ruipu Wu, Rushuai Yang, Houlin Li, Shukai Yang, Jing Wu, Yuxiang Yan, Yongcheng Liu, Chuankang Li, Guanghui Ren, Wei Shan, Maoqing Yao
arXiv Machine Learning
Sep 21

From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention

The paper introduces PARTS, a real‑world subtask reinforcement learning framework that fine‑tunes a pretrained robot policy by focusing on critical bottleneck subtasks while keeping the base policy frozen. It uses agent‑generated selectors and success verifiers to provide local rewards, enabling learning even when full‑task successes are rare. Experiments on bimanual YAM and single‑arm Franka robots show that PARTS raises complete‑task success from 32% to 61% and from 50% to 95%, respectively, with only tens of minutes of real‑world RL rollouts and minimal human intervention.

By Sichang Su, Benjamin Yang, Zhiyun Deng, Boyuan Liang, Yip Fun Yeung, Zelin Wang, Lingfeng Sun
arXiv AI
Aug 19

EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models

EXPO-FT is a system that enables stable, sample‑efficient reinforcement learning fine‑tuning of pretrained Vision‑Language‑Action (VLA) policies. It achieves perfect success on a range of manipulation tasks—such as routing string lights, striking a pool ball, and inserting a flower into a wine bottle—using only about 19.1 minutes of online robot data. The approach outperforms both RL-from-scratch and existing VLA fine‑tuning methods, and the authors provide an open‑source codebase to support wider adoption.

By Perry Dong, Kuo-Han Hung, Tian Gao, Dorsa Sadigh, Chelsea Finn
arXiv AI
Oct 27

RoboGene: Diversity-Driven Agentic Task Generation Framework for VLA Pre-training

RoboGene is an agentic framework designed to generate diverse and informative manipulation tasks for single-arm, dual-arm, and mobile robots. It employs diversity-driven sampling, agentic self-reflection for task quality assessment, and human-verified feedback memory to validate and refine tasks. The framework produced 18,000 real-world trajectories and introduced new metrics for task feasibility and diversity, outperforming models like GPT‑4o and Gemini 2.5 Pro in training VLA models that achieve higher success rates and stronger generalization.

By Yixue Zhang, Kun Wu, Zhi Gao, Zhen Zhao, Pei Ren, Zhiyuan Xu, Fei Liao, Xinhua Wang, Shichao Fan, Di Wu, Qiuxuan Feng, Meng Li, Zhengping Che, Chang Liu, Jian Tang
arXiv AI
Jun 11

Vision-Language-Action Jump-Starting for Reinforcement Learning Robotic Agents

arXiv:2604. 13733v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit assignment.

By Angelo Moroncelli, Roberto Zanetti, Marco Maccarini, Loris Roveda
arXiv AI
Nov 6

Vision-Language Models Are Joint Denoisers in Robotic Action Generation

Vision‑Language Models Are Joint Denoisers in Robotic Action Generation introduces JADE, a Joint Action DEnoiser that lets a pretrained vision‑language model (VLM) and a diffusion action expert jointly refine actions. By structuring action latents, the VLM can read noisy actions alongside visual observations and language instructions, guiding the action expert through gated cross‑attention at each denoising step. This joint denoising reduces sampling steps, balances performance and latency, and improves success rates on RoboDojo and RoboTwin 2.0 compared to prior methods.

By Xicheng Gong, Wenxuan Song, Chengze Liu, Qiwei Li, Qize Yu, Jiaolong Yang, Haoang Li, Yadong Mu
arXiv AI
Jul 14

Maximizing Human Efficiency in Large-Scale Robot Post-Training via VLAC-Cut Guided Pipeline

arXiv:2607. 09776v1 Announce Type: cross Abstract: When adapting Vision Language Action (VLA) models to downstream tasks, multiple rounds of post training are required because a single round of data cannot resolve all issues, making continuous iterations necessary to progressively address the weaknesses exposed in previous rounds.

By Shaopeng Zhai, Qi Zhang, Tianyi Zhang, Haoran Zhang, Fuxian Huang, Zhanhui Lin, Zijun Xu
arXiv Machine Learning
Oct 12

RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation

RARA (Retrieval‑Anchored Representation Alignment) is a two‑stage method for fine‑tuning pre‑trained robot policies on new tasks with few demonstrations. It first retrieves and aligns representations from pre‑training that match the target task’s intent and motion, then fine‑tunes while constraining changes to those retrieved representations. Experiments on Diffusion Policy and GR00T across 13 tasks in simulation and on a real robot show RARA improves in‑distribution success by 9.5 points and out‑of‑distribution success by 13.6 points, outperforming all baselines.

By Xuhui Kang, Sung-Wook Lee, Yan Zhuang, Tianle Zhong, Yen-Ling Kuo